Category: AI & Other Tech

  • So, I asked Claude to enhance its response from 3rd party sources if there was anything notable – and to conduct a fact check. The good part about all this?

    What was added

    The only section that warranted substantive enhancement based on third-party sources was “Discovery and Response.”The original draft characterized AEL’s reaction to the June 2025 public reports as a clean, cooperative pivot. Third-party reporting reveals a more complicated picture:

    • The trigger was specifically the Wall Street Journal‘s investigative report tracking LPG tankers between Gulf ports and Mundra Port — worth naming rather than leaving as generic “public reports.”
    • At the same moment AEL was suspending imports and retaining U.S. counsel privately, it was publicly filing a stock exchange statement calling the allegations “baseless and mischievous” and denying awareness of any investigation. This tension is directly material to understanding why the case doesn’t qualify for voluntary self-disclosure credit.

    One minor enhancement in the Mitigating Factors section: AEL’s own public statements confirmed the “less than 1.5%” revenue figure at 1.46% specifically, so that precision was added there.

    No factual corrections were required — the enforcement release is well-supported by contemporaneous reporting on the underlying facts.

    Additional sources consulted:

    • Wall Street Journal — investigative report on Adani LPG tankers (June 2, 2025); original source that triggered the public reports referenced in the enforcement release
    • Adani Enterprises stock exchange filing (June 2025) — via multiple Indian financial press outlets (Business Upturn, MENAFN, Outlook Business, Lokmattimes)
    • BloombergReuters/U.S. NewsIANSBizzBuzz News — day-of settlement reporting confirming key facts (May 18, 2026)
    • The Tribune IndiaDT NextThe Federal — pre-settlement reporting (May 15, 2026) on the broader Adani Group legal resolution context

    The bad part? I didn’t tell it to make a new post with the additional info – so it updated the post. Oopsie! But I like this, so I will amend my base prompt for enforcement actions to do this same thing for all future enforcement action posts.

  • My initial prompt to Gemini:

    Why did OFSI extend the expiration date of General Licence INT/2026/8893924 until July 8th?

    The initial response:

    The Office of Financial Sanctions Implementation (OFSI) extended the expiration date of General Licence INT/2026/8893924 (the “Maritime Mutual Re-Insurance Wind Down” licence) to July 8, 2026, primarily to provide additional time for the orderly winding down of complex insurance and reinsurance contracts.

    The extension, which was announced on April 9, 2026 (the original expiry date), follows several key factors:

    1. Complexity of Maritime Insurance

    Maritime Mutual entities were designated on February 24, 2026, as part of a major sanctions package targeting Russia’s “shadow fleet.” Because insurance and reinsurance policies—particularly Protection and Indemnity (P&I) cover—involve long-tail liabilities and intricate regulatory requirements, the initial six-week wind-down period proved insufficient for UK insurers and brokers to legally exit or transfer these contracts.

    2. Industry Feedback

    The extension likely responds to feedback from the London insurance market and global maritime stakeholders. Winding down cover for hundreds of vessels simultaneously requires time to:

    • Identify all underlying risks.
    • Process necessary cancellations and premium refunds.
    • Ensure that vessels have sufficient time to seek alternative, compliant cover to meet international maritime conventions.

    3. Orderly Market Exit

    By extending the deadline to July 8th, OFSI aims to mitigate the risk of accidental breaches and prevent immediate, disorderly disruptions in the maritime sector. The licence permits UK persons to receive, process, and transmit funds or economic resources to “extricate themselves” from contracts written prior to the February 24th designation.


    Key Details of the Licence

    FeatureDetails
    Licence ReferenceINT/2026/8893924
    Entities InvolvedMaritime Mutual Association Limited (Gibraltar), Maritime Mutual Insurance Association (NZ) Limited, and their subsidiaries.
    Current Expiry23:59 on July 8, 2026
    PermissionsWinding down, cancelling, or terminating insurance/reinsurance contracts agreed in writing before Feb 24, 2026.

    … you might find it interesting that this extension coincides with a broader OFSI effort to manage the high volume of licensing applications, which reached over 900 in the previous fiscal year.

    This looked reasonable, but I was curious as to what Gemini was inferring rather than knowing. So…

    provide a source list for your response. Is any part of your response not supported by the sources?

    And here’s Gemini checking its work:

    My previous response was based on official UK government updates and industry analysis typical of such sanctions developments. Below is the source list and a breakdown of what is explicitly stated versus what is inferred based on regulatory context.

    Source List

    1. Office of Financial Sanctions Implementation (OFSI):
    2. HM Treasury – UK Sanctions List:
      • Designation entries for Maritime Mutual Association Limited and Maritime Mutual Insurance Association (NZ) Limited (February 24, 2026).
    3. Legal & Industry Trackers (Secondary Sources):
      • Ashurst Russia Sanctions Tracker (UK): Update for April 2026 detailing the extension of wind-down periods.
      • LexisNexis Corporate Crime Highlights: Entry dated April 9, 2026, regarding the Maritime Mutual extension.
      • Insurance Business Mag: “Maritime Mutual added to UK Russia sanctions list” (February 26, 2026), providing context on the “shadow fleet” and P&I cover.

    Support Analysis

    While the primary facts are strictly supported by the official record, the qualitative “reasons” for the extension involve a degree of synthesis.

    Part of ResponseSupported by Sources?Note
    New Expiry (July 8, 2026)YesExplicitly stated in the amended GL and Publication Notice (April 9, 2026).
    Announcement Date (April 9)YesThe date the amendment was published on GOV.UK.
    Designation Context (Feb 24)YesMatches the date Maritime Mutual was added to the UK Sanctions List.
    Reasons: “Complexity” & “Industry Feedback”PartialOFSI notices are typically technical; they rarely list “industry feedback” in the text of the licence itself. However, these are the standard justifications cited by legal experts (e.g., Ashurst, Baker McKenzie) and are consistent with OFSI’s “Reasonableness in licensing” policy published in March 2026.
    “Shadow Fleet” MentionContextualThis is the official reason for the original designation (supporting Russian energy exports via non-compliant vessels), but the extension notice doesn’t repeat this—it only references the DP (Designated Person).

    Is any part not supported?

    The specific claim that the extension was due to “London insurance market feedback” is an expert inference. While historically true for almost all OFSI maritime insurance extensions (like the previous LUKOIL or GTLK wind-downs), the April 9th publication notice for INT/2026/8893924 technically only lists the amendment to the date without a detailed “Statement of Reasons” for the extension itself.

    Sounds reasonable to me – what do you think?

  • Given your knowledge of OFAC updates, advisory and guidance documents, and sanctions-related press releases from the State and Treasury departments, and the wording of sanctions-related Executive Orders, create a fictitious “update” for April Fool’s Day. Make it not so believable that many readers will think it’s real  , but not so absurd that people will realize it’s a joke immediately.

    ,
  • UK Gov logo, 50% resolution.png

    UK Sanctions List Search Tool: User Guide

    We have published a user guide to accompany the UK Sanctions List search tool. It sets out the functions and features of the search tool, how it works and how to use it.

    The user guide helps to explain a number of features to help determine if a person, entity, or ship is included on the UK Sanctions List. These include:

    • Exact matches and partial matches of a search term
    • Fuzzy searching
    • Exact word or phrase
    • Highlighting of search matches
    • Multi-select filters 
    • Search URLs 
    • Results ranking  

    Contents

    1. Overview of search features
    2. How the search works
    3. Widening your search with fuzzy search
    4. Search for exact phrases using quotation marks
    5. Highlighting of search matches
    6. Using filters to narrow your search
    7. Search URLs
    8. How results are ranked
  • My prompts to Gemini:

    Please identify trends for: a) 2025 as compared to the years 2015 to 2024, inclusive b) the years 2023 to 2025, inclusive as compared to the years 2015 to 2022, inclusive c) the years 2021 to 2025, inclusive as compared to the years 2015 to 2020, inclusive. Please wait for clarification as to what I am looking for before proceeding.

    Identify trends in a) specific behaviors or failures, such as wire stripping, lack of DNS or other internet-based checks, or ignoring internal whistleblower warnings b) size of assessed penalties or settlement amounts c) size of base penalties d) the combination of the egregiousness factor and voluntary self-disclosure factor e) the industries of the firm involved f) the ratio of financial services firms penalized vs. non-financial firms penalized g) the aggravating factors noted h) the mitigating factors noted g) the general timeframe of the violations (e.g. 2 years, 3 months duration) h) the amount of time between the end of the violating behavior and the settlement i) any other patterns you can identify… Lastly, if you infer something other than what is explicitly named in the enforcement notices (and/or settelement agreements, if available), please identify it as such and explain your reasoning.

    please add for each insight the number of matching actions that fit the insight, and the percentage of each population that represents (example: 4 enforcement actions of 12 total, would be represented similarly to “4 enforcement actions, 33% of total). Use whole percentages only

    After a few extra refining steps, I got back this:

    Based on the enforcement actions published by OFAC through the end of 2025 (Total Population: 14 actions), and historical data from previous years, here is the trend analysis with the requested level of detail and corrected distributions.

    Trend Analysis by Time Period

    a) 2025 vs. 2015–2024

    • Rise of the “Gatekeepers”:
      • Trend: In 2025, OFAC heavily targeted firms that manage wealth or property rather than just moving funds. 5 of the 14 enforcement actions (36%) were levied against Venture Capital, Private Equity, Holding Companies, or Real Estate firms. This is a sharp deviation from the 2015–2024 average, where such “gatekeeper” actions typically represented less than 5% of the annual caseload.
      • Matching Actions (2025): GVA CapitalGracetown Inc.IPI PartnersKey HoldingFamily International Realty.
    • Individual Liability:
      • Trend: There was a significant spike in penalties assessed against specific persons rather than corporate entities. 3 of the 14 actions (21%) in 2025 explicitly named “An Individual” or a specific person alongside a small entity. In the 2015–2024 period, actions against individuals were rare outliers (often 0% to 5% of annual cases).
      • Matching Actions (2025): An Individual (Dec 9)An Individual (Nov 24)Family International Realty (and an Individual).

    b) 2023–2025 vs. 2015–2022

    • Crypto & Fintech Focus:
      • Trend: The 2023–2025 period solidified the Virtual Currency sector as a primary enforcement target. 11 of the ~43 enforcement actions (approx. 26%) over this three-year period involved crypto exchanges, wallet providers, or fintech platforms. In contrast, during the 2015–2022 era, this sector represented fewer than 5% of total actions.
      • Matching Actions (2025 examples): Exodus MovementShapeShift AGInteractive Brokers.
    • Decline of Tier 1 Banks:
      • Trend: Traditional commercial banks have nearly vanished from the enforcement list. In the 2023–2025 period, traditional banks accounted for less than 10% of actions. This compares to the 2015–2019 period, where banks frequently constituted 30–50% of the annual lists due to the “wire stripping” sweeps.

    c) 2021–2025 vs. 2015–2020

    • The Russia Shift:
      • Trend: Driven by the 2022 invasion of Ukraine, the focus of enforcement has shifted decisively to Russia. In 2025 alone, at least 5 of the 14 actions (36%) were primarily driven by Russia/Ukraine-related sanctions (targeting oligarch assets or industrial exports). Across the 2021–2025 window, Russia cases represent approximately 30–40% of volume, whereas the 2015–2020 period was dominated by Iran, Cuba, and Sudan cases (often >60%).

    Detailed Factor Analysis (2025 Data Focus)

    • a) Specific Behaviors:
      • Gatekeeper Negligence: 5 actions (36%) involved trust or investment firms failing to identify that their ultimate beneficiary was a blocked person.
      • IP/Geolocation Failures: 3 actions (21%) explicitly cited the failure to use available IP address data to block users in sanctioned jurisdictions (e.g., Interactive BrokersExodusShapeShift).
    • b) Size of Assessed Penalties (Corrected Distribution):
      • Mega-Penalty (> $20 Million):1 action (7%).
        • Detail: GVA Capital ($216M). This single outlier accounted for the vast majority of the total dollar value.
      • Middle Market ($1 Million – $12 Million):11 actions (79%).
        • Detail: This was the dominant tier for 2025, comprising nearly 80% of all cases. Unlike previous years which saw many small settlements, 2025 saw a high floor for penalties.
        • Matching Actions: Interactive Brokers ($11.8M), IPI Partners ($11.5M), Gracetown ($7.1M), Individual($4.7M), Unicat ($3.9M), Exodus ($3.1M), Fracht ($1.6M), Harman ($1.45M), Individual ($1.1M), Family Realty ($1.1M), Haas ($1.0M).
      • Small Penalties (< $1 Million):2 actions (14%).
        • Detail: Only two cases fell below the million-dollar mark, a significant decrease in the frequency of “slap on the wrist” settlements compared to prior years.
        • Matching Actions: ShapeShift AG ($750k), Key Holding ($608k).
    • c) Industries Involved:
      • Investment/Wealth Management: 5 actions (36%) (VC, PE, Holding).
      • Tech/Fintech/Crypto: 3 actions (21%).
      • Manufacturing/Logistics: 3 actions (21%) (HaasHarmanUnicat).
    • d) Egregiousness & VSD:
      • High Severity: While exact determinations vary, the high proportion of penalties exceeding $1 million (93% of cases) suggests a trend toward viewing 2025 violations as substantive rather than merely procedural.
    • e) Aggravating Factors:
      • Individual Recklessness: Explicitly noted in 3 actions (21%) where individuals were personally fined.
      • Reason to Know: Cited in 3 actions (21%) (Tech/Crypto) where the firm possessed IP data but failed to utilize it for screening.
    • f) Timeframe of Violations:
      • Pre-2022 Conduct: 12 of 14 actions (86%) involved conduct that began before or during 2022. This reinforces the 3–5 year lag between violation and enforcement.
    • g) Inferred Patterns:
      • Whistleblower Driven: The enforcement against small private firms and individuals (approx. 20–30% of cases) strongly implies reliance on whistleblower tips or specific intelligence, as these entities lack the transaction volume to trigger automated bank filters.

    Interesting insights… did you notice anything else? I asked for those percentages because Gemini originally over-emphasized that one really large settlement, giving it a lot more significance than perhaps it deserved. 7 percent, sure… but still only one action. A single data point does not make a trend.

    And, due to the generally low number of enforcement actions, total, take this with a grain of salt. You’ll notice how Gemini highlighted the rise of Russia-related actions after 2022 – thanks, Captain Obvious! Sure, there were the Ukaine/Russia-related sanctions after 2014, but…

    Nonetheless, there are insights to be cognizant of, that perhaps should be given more consideration.

    , ,
  • This is the prompt I use to pretty-print OFAC designation-related information – feel free to suggest improvements or point out issues (yes, I know telling it to output a carriage return is pretty dumb because Gemini uses Markdown format – I will clean that up eventually, but right now, it still “works:):

    Throughout this procedure, make field names and the colon bold, but leave the field value normally formatted.

    Do not infer information about a listing from an associated listing that references it – only output information from the actual listing.

    Provide no citation markers. However, if any sources other than the update site or the press release are referenced, provide a source list at the end.

    First, output a heading, with H1 heading formatting, with the title  of the update, followed by a carriage return – and make it a hyperlink to the update URL.

    If there was a press release, output the name of the issuing body (e.g. “State” or “Treasury), followed by“ Press Release: “, followed by the title of the press release, for each press release.. Ensure the press release title is made into a hyperlink to the corresponding press release URL, and format the whole line as an H3 header.

    If there are sections of additions:

    Output “Additions:” with H2 heading, and bold.

    Output a carriage return.

    For each listing in each section of additions:

    Reformat each listing:

    Output the name, bolded. If a vessel with a call sign, output a space, then the call sign in parentheses

    Then produce the rest of the data as a bulleted list:

    1. If there are AKAs, list those prefaced by “AKA: “ and make that label bold. If there are multiple AKAs, put the label on the bullet, and make each AKA a separate sub-bullet, If there is only 1 AKA, put the AKA on the same line as the label
    2. For vessels, if vessel type found, output the vessel type, prefaced by “Vessel Type: ”
    3. For vessels, if vessel flag country found, output the vessel flag country, prefaced by “Vessel Flag: ”
    4. List remaining fields in order of their presence. However, do not list the program tags. Bold the field name.
    5. If there is a listed party type, list it, prefaced by “Party Type: “. Bold the label
    6. If there are associated “Linked to:” parties in parentheses, output “Linked to: “ and that information. If there are multiple Linked To parties, make the label the main bullet, and make the parties separate sub-bullets. Make the label  bold.

    Next, add supplemental information from the  press release linked to in the update, if any, as well as any  publicly-available information that can be reliably linked to each listed party. Preface this with “Supplemental Information: “, bolded – but not bulleted to offset it from the bulleted items

    Then output two carriage returns.

    Preface each section divided by type of party (e.g. individuals, entities, \ vessels, aircraft) and by the list updated (e.g. SDN, SSI, FSE) with the section header from the OFAC designation update – for example, “The following entities have been added to OFAC’s SDN List:”. Make the section header ,  italicized and bolded.

    Group listings within each section by the combination of program tags.

    Preface each grouping with a list of the associated program tags, followed by the description from OFAC’s program tag web page.  If there is a single program tag, output :OFAC Program:  “, followed by the program tag, 2 spaces, a and its description. If there are multiple program tags, make a bulleted list, with “OFAC Programs:” on the first bullet, and each program tag, 2 spaces, and its description, on a new sub-bullet. Make this italicized.

    Output two carriage returns between listings within each section

    End of additions section logic

    If there are sections of deletions, removals or delistings:

    Output “Delistings:” with H2 heading formatting, bolded.

    Output a carriage return.

    Preface each section divided by type of party (e.g. individuals, entities, \ vessels, aircraft) and by the list updated (e.g. SDN, SSI, FSE) with the section header from the OFAC designation update – for example, “The following deletions have been made to OFAC’s SDN List:”. Make the section header ,  italicized and bolded.

    Display each listing, removing the program tags from the end of the listing. Bold each field name. To clarify, this is a different format than that of the additions section – since these are removals, we do not need to highlight each field by putting them on separate lines.

    Group listings  by the combination of program tags.

    Preface each grouping with a list of the associated program tags, followed by the description from OFAC’s program tag web page.  If there is a single program tag, output :OFAC Program:  “, followed by the program tag, 2 spaces, a and its description. If there are multiple program tags, make a bulleted list, with “OFAC Programs:” on the first bullet, and each program tag, 2 spaces, and its description, on a new sub-bullet. Make this italicized.

    Output two carriage returns between listings 

    End of deletions, removals or delistings section logic

    If there are sections of changes: 

    Do not process the “unrelated administrative list changes” section if the next line of text says “None”

    Output “Amendments:” with H2 heading formatting, bolded.

    Output a carriage return.

    Preface each section with the section header from the OFAC designation update.

    Make the section header , italicized and bolded.

    Reformat each listing:

    For the new version of the listing:

    a) Output the name, bolded

    b) Then produce the rest of the data as a bulleted list:

    1. If there are AKAs, list those prefaced by “AKA: “ and make that label bold. If there are multiple AKAs, put the label on the bullet, and make each AKA a separate sub-bullet, If there is only 1 AKA, put the AKA on the same line as the label
    2. List remaining fields in order of their presence. However, do not list the program tags. Bold the field name.
    3. If there is a listed party type, list it, prefaced by “Party Type: “. Bold the label
    4. If there are associated “Linked to:” parties in parentheses, output “Linked to: “ and that information. If there are multiple Linked To parties, make the label the main bullet, and make the parties separate sub-bullets. Make the label  bold.

    c) Next, add supplemental information from the  press release linked to in the update, if any, as well as any  publicly-available information that can be reliably linked to each listed party. Preface this with “Supplemental Information: “, bolded – but not bulleted to offset it from the bulleted items

    d) Then output two carriage returns.

    e) Then, Output “List of Changes:” followed by a carriage return. Make this italicized and bolded.

    Make a bulleted list of every field in the listing that has changed:

    1. Output “Field Name: “, List the field name
    2. If there is a new value and no old value, output “Added: “ and the new value as a sub-bullet
    3. If there is an old value and no new value, output “Deleted: “ and the old value as a sub-bullet
    4. If there are new and old values, output “Changed: “, the old value, “ to: “ and the new value as a sub-bullet

    End of listing reformatting. 

    Group listings  by the combination of program tags.

    Preface each grouping with a list of the associated program tags, followed by the description from OFAC’s program tag web page.  If there is a single program tag, output :OFAC Program:  “, followed by the program tag, 2 spaces, a and its description. If there are multiple program tags, make a bulleted list, with “OFAC Programs:” on the first bullet, and each program tag, 2 spaces, and its description, on a new sub-bullet. Make this italicized.

    Insert two carriage returns between listings 

    End of changes section logic

    Finally, if there is a press chart, output “Press Chart: “, followed by the press chart .  Make the chart image a hyperlink to the press chart URL. Make the whole press chart section an H3 heading.

    , ,
  • I’ve been working on this for a while – as a learning tool, correcting and refining is more instructive to me than getting a good result and asking for the master prompt.

    A few things to point out:

    • I haven’t run this against aircraft designations “live” yet, so this part might not be precise
    • OFAC doesn’t use any delimiters except for things that can have multiple values, so you don’t know, at a glance, when a field’s label ends and its value begins. I’ve generally steered Gemini by listing all the labels I’ve seen
    • Sometimes OFAC doesn’t break down the data at all – cargo vessel types are immediately followed by the flag state with delimiter (although I guess you could treat the whole thing as a compound data element)
    • OFAC clearly has a bias towards sanctioning entities – why else would there be party types of “aircraft”, “vessel” and “individual”, but nothing for entities?

    Anyhow, here’s the prompt – if you see some logic that will break, let me know:

    OFAC addition or deletion listings are in the following format:

    All OFAC listings finish with the following:

    1. The type of party (Individual, Vessel, Aircraft) in parentheses may be present- if not present, the listing refers to an entity. Entities can also be identified more easily if the section of the OFAC identifies the listings which follow as entities.
    2. After that. a series of OFAC program tags (defined at Information on OFAC sanctions lists program tags and their definitions.),appears, in square brackets – there will always be at least one.
    3. Next, optionally, in parentheses, the text “Linked To:” and other parties with which the listed party is associated, with multiple instances separated by semi-colons
    4. And the listing terminates with a period.

    And the first element in all listings is the primary name.

    The information between the primary name and the party type depends on the party type:

    For entities:

    1. After the primary name, in parentheses, is  an optional series of aliases, prefixed by “a.k.a.” and separated by semicolons
    2. Next, after a comma, are associated addresses, each followed by a semicolon
    3. Next are a series of fields consisting of labels (e.g. Identification Number, Registration number), possibly terminated with a colon (e.g. “Secondary sanctions risk:”), a value, and terminated by a semicolon, except for the last field
    4. The Registration Number field may have subfields such as issuing country (in parentheses) and issue date.
    5. As a reminder, the final field is not terminated by a semi-colon but is followed by the list of program tags, the optional Linked To information and the final period.

    Here is an example: 

    ARIES GLOBAL INVESTMENT LTD (a.k.a. ARIES GLOBAL INVESTMENT LIMITED), Room 2611, 26th Floor, Southeast Technology R&D Center, 438, Jincheng Lu, Xiaoshan Qu, Hangzhou, Zhejiang, China; Rm A 20/F ZJ 300, 300 LOCKHART RD, Wan Chai, Hong Kong, China; Identification Number IMO 0052971; Registration Number 76957722 (Hong Kong) issued 19 Aug 2024 [VENEZUELA-EO13850]. 

    For individuals:

    1. After the primary name, in parentheses, is either a series of aliases, prefixed by “a.k.a.” and separated by semicolons, or a vessel call sign
    2. After a comma, are associated addresses (full address, city and country or country), each followed by a semicolon
    3. Next are a series of fields consisting of labels (e.g. DOB, nationality, Gender, Secondary Sanctions Risk, Cedula, possibly terminated with a colon (e.g. Secondary sanctions risk:), a value, and terminated by a semicolon, except for the last field
    4. As a reminder, the final field is not terminated by a semi-colon but is followed by the party type in parentheses, the list of program tags, the optional Linked To information and the final period.

    Here is an example: 

    ARAYA NAVARRO, Jimena Romina (a.k.a. “ARAYA, Jimena”; a.k.a. “Rosita”), Venezuela; Colombia; DOB 05 Sep 1983; nationality Venezuela; Gender Female; Secondary sanctions risk: section 1(b) of Executive Order 13224, as amended by Executive Order 13886; Cedula No. 16011070 (Venezuela) (individual) [SDGT] [TCO] (Linked To: TREN DE ARAGUA). 

    For cargo vessels:

    1. After the primary name, optionally, in parentheses, a vessel call sign appears
    2. Next appears a description of the vessel, and the flagging country, with multiple instances separated by semi-colons (and subsequent ones may be preceded by “Other Vessel Flag”
    3. Next are a series of fields consisting of labels (e.g. Year of Build, Identification Number, Registration number, MMSI), possibly terminated with a colon (e.g. Secondary sanctions risk:), a value, and terminated by a semicolon, except for the last field
    4. As a reminder, the final field is not terminated by a semi-colon but is followed by the party type in parentheses, the list of program tags, the optional Linked To information and the final period.

    Here is an example: 

    VALIANT (VRXH3) Crude Oil Tanker Hong Kong flag; Other Vessel Flag China; Vessel Year of Build 2009; Vessel Registration Identification IMO 9409247; MMSI 477206500 (vessel) [VENEZUELA-EO13850] (Linked To: ARIES GLOBAL INVESTMENT LTD).

    For aircraft:

    1. After the primary name, there is a semi-colon
    2. Next are a series of fields consisting of labels (e.g. Manufacture Date, Model, Operator, Manufacturer’s Serial Number (MSN), Tail Number), possibly terminated with a colon (e.g. Secondary sanctions risk:), a value, and terminated by a semicolon, except for the last field
    3. As a reminder, the final field is not terminated by a semi-colon but is followed by the party type in parentheses, the list of program tags, the optional Linked To information and the final period.

    Here is an example: 

    EP-MJG; Aircraft Manufacture Date 2002; Aircraft Model Airbus A340-300; Aircraft Operator Mahan Air; Aircraft Manufacturer’s Serial Number (MSN) 474; Aircraft Tail Number EP-MJG; Secondary sanctions risk: section 1(b) of Executive Order 13224, as amended by Executive Order 13886 (aircraft) [SDGT] [IFSR] (Linked To: MAHAN AIR). 

    OFAC change listings consist of the old listing, followed by “-to-“, followed by the new listing.

    Take no action on this information until prompted further.

  • Ok, Ok… yes, it’s a controversial title… but you’re reading the post, right? And there is a reason for it, just wait….

    So, there’s been a push over quite a few years to designate quite a few Iranian entities under the OFAC counter-terrorism program. I wondered how many there were, so I asked Gemini.

    The answer: 666 (see what I did there?)

    Now, a few technical things – this was nowhere near the first total I got. I initially asked for a list of parties that had both Iran-related and counter-terrorism-related program tags – and I got back 10 rows. It took a few iterations – and instructions to identify the right tags by looking at the program tag definition page and use all the ones associated with Iran and counter terrorism. But that left me only at 32… which made no sense.

    So, I asked it where it got the data from…

    I sourced the data for the CSV file directly from the examples and information retrieved during our conversation, specifically from the U.S. Department of the Treasury’s Office of Foreign Assets Control (OFAC) Recent Actionsupdates we processed together (from December 2025 back to December 2024) and the OFAC Program Tag Definitionspage I accessed.

    To be specific:

    1. Recent Actions Updates: The individuals like Ahmad GhaediHamidreza Heidari, and the Lashgarian family members were pulled from the February 2024 and December 2025 updates we discussed, where they were designated under both counter-terrorism (SDGT) and Iran-related authorities (IFSR/IRGC).
    2. Established Designations: Major entities like the IRGCBasij Resistance ForceMahan Air, and Bank Saderat are historical, well-known dual-designated entities that appear frequently in OFAC’s public enforcement data and were referenced in the “Linked To” fields of the updates we processed.
    3. Program Tag Definitions: I used the official OFAC definitions page (which I accessed in the previous step) to ensure I was capturing the correct codes (e.g., distinguishing that NPWMD is a proliferation tag often used alongside Iran tags, while SDGT and FTO are the specific counter-terrorism tags).

    The dataset I generated was a representative sample constructed from these specific sources to demonstrate the formatting and logic you requested, rather than a direct download of the entire OFAC SDN list database.

    Would you like me to show you how to download the complete and official raw data files directly from the Treasury Department’s website for comprehensive analysis?

    I asked it to go get one of the SDN List files from the OFAC website… and apparently, at my personal use level, it couldn’t do that. Ultimately, I got the file myself and uploaded it to Gemini – that got me to 666.

    Now, for the fun, non-technical piece of the puzzle: did these all fit under what we would consider “terrorists”?

    I cannot provide personal opinions or make subjective determinations about whether specific sanctions designations are “fair” or “unfair,” nor can I definitively conclude which parties meet a common definition of “terrorism” versus those that do not. The designation of entities under counter-terrorism authorities is a legal and policy determination made by the U.S. government based on classified and unclassified intelligence.

    However, I can analyze the publicly stated reasons provided by the U.S. Treasury and State Departments for these designations. This allows you to see the specific activities cited by the government that led to the application of counter-terrorism sanctions (such as SDGT or FTO tags) alongside Iran-related tags.

    Analysis of Designations: Rationale vs. Common Definitions

    The entities in your dataset (those with both Iran-related and Terrorism-related tags) generally fall into three primary categories based on OFAC’s designation criteria:

    1. Direct Terrorist Activity & Support:
      • Entities: IRGC, IRGC-Qods Force, Kata’ib Hizballah, Asa’ib Ahl al-Haq, Hizballah.
      • Stated Rationale: These groups are often designated as Foreign Terrorist Organizations (FTO) or Specially Designated Global Terrorists (SDGT). The U.S. government cites direct involvement in acts of violence, bombings, kidnappings, and military operations outside of Iran (e.g., in Syria, Iraq, Lebanon, Yemen) that target U.S. personnel or civilians.
      • Relation to Definition: These justifications align closely with standard definitions of terrorism involving politically motivated violence against non-combatants.
    2. Financial & Material Support (Facilitators):
      • Entities: Bank Saderat, Bank Mellat, Mehr Eghtesad Bank, Bonyad Taavon Basij, and various investment companies (e.g., Mehr Eghtesad Iranian Investment Company).
      • Stated Rationale: These entities are designated under counter-terrorism authorities (SDGT) not because they commit violent acts themselves, but because they provide “material support” (financial services, funding, logistics) to designated terrorist groups like the IRGC-QF or Hizballah. For example, moving funds to pay fighters or procuring technology for weapons programs.
      • Relation to Definition: While these are banks or investment firms, the “material support” provision in U.S. law allows for their designation under terrorism authorities. A layperson using a strict dictionary definition of “terrorist” (one who commits violence) might view these designations as distinct, but under U.S. sanctions law, financing terrorism is treated with equal severity.
    3. Logistical & Technological Support:
      • Entities: Mahan Air, Caspian Air, various industrial groups (Shahid Hemmat, Shahid Bakeri), and individual procurement agents (e.g., Ghaedi, Heidari).
      • Stated Rationale: Airlines are often designated for transporting personnel and weapons for the IRGC-QF to conflict zones. Industrial groups are designated for developing ballistic missiles or UAVs used by these groups.
      • Relation to Definition: Similar to financial facilitators, these entities are designated for enabling the operations of the primary terrorist groups.

    Summary of the 666 Rows

    • Total Rows: 666
    • “Unfair” Determinations: 0 (As an AI, I cannot label a legal designation as unfair).
    • “Fair” Determinations: 0 (As an AI, I cannot validate the government’s classified intelligence).

    Conclusion based on Public Record:

    Every entity in the dataset has a specific legal basis for its designation published by the U.S. Treasury.

    • Violent Groups: The core groups (IRGC, militias) are designated for direct violent activities.
    • Support Network: The majority of the 666 rows (banks, individuals, companies) are designated for providing support to those core groups.

    Yes, I know it was dumb to ask it if the designation was “fair” – but it did get me to what I wanted to know…

    But the military groups like the IRGC still confused me, so I asked it how that was different from Russia invading Ukraine:

    how are “military operations outside of Iran” considered “terrorism” rather than military operations like the Russian invasion of Ukraine?

    and the response:

    The distinction you are asking about touches on one of the most complex and debated areas of international law and U.S. foreign policy.

    In general, the U.S. government and international law distinguish between “acts of war” (conducted by state militaries) and “terrorism” (conducted by non-state actors).

    The Russian military is considered a state armed force engaged in a conventional (albeit illegal) war, while the IRGC is treated as a “hybrid” entity that uses terrorism as a primary tool of statecraft.

    Here is the detailed breakdown of how the U.S. government makes that legal and policy distinction:

    1. The “Law of War” vs. “Terrorism” Framework

    • State Militaries (Russia): Under the Geneva Conventions and U.S. law, uniformed armed forces of a sovereign state are considered “lawful combatants.” When they cross a border to fight, they are engaging in an armed conflict.
      • If they kill civilians or bomb hospitals, those are War Crimes, not “terrorism.” War crimes have their own set of laws (laws of armed conflict) and tribunals (like the ICC).
      • Why this matters: If a Russian soldier kills a Ukrainian soldier on the battlefield, it is not a crime; it is an act of war. If a terrorist kills a soldier, it is a crime (murder/terrorism) because they have no “combatant privilege.”
    • Terrorist Groups: Terrorism is typically defined in U.S. law (18 U.S. Code § 2331) as violent acts intended to coerce a civilian population or influence a government, usually committed by sub-national groups or clandestine agents.1

    2. The Exception: Why the IRGC is Designated “Terrorist”

    For decades, the standard rule was that state militaries could not be “terrorists.” However, the U.S. designated the Islamic Revolutionary Guard Corps (IRGC) as a Foreign Terrorist Organization (FTO) in 2019—the first time a state entity received this designation.2

    The U.S. justified this exception by arguing that the IRGC operates fundamentally differently from a normal military:

    • Use of Proxies: Unlike the Russian army, which deploys its own uniformed troops to hold territory, the IRGC often exports violence through non-state “proxy” groups (like Hezbollah, Kata’ib Hizballah, or the Houthis). The U.S. views the IRGC as the “handler” for these terrorist organizations.
    • Clandestine Operations: The IRGC-Qods Force specializes in covert assassinations, bombings, and kidnappings outside of defined war zones (e.g., plots in Europe, South America, or the U.S.) rather than conventional battlefield maneuvers.
    • Material Support: The designation focuses heavily on the IRGC funding, training, and equipping designated terrorist groups, making them a “terrorist facilitator” in the eyes of the law.3

    3. Why the Russian Military is Not Designated an FTO

    Despite the documented atrocities in Ukraine, the U.S. has resisted designating the Russian military as a Foreign Terrorist Organization or Russia as a “State Sponsor of Terrorism.”

    • Conventional Warfare: The invasion of Ukraine is viewed as a conventional state-on-state conflict. Even though it is an act of aggression, it fits the legal definition of “war” rather than “terrorism.”
    • Diplomatic & Legal Risks: Designating a state military (especially a nuclear superpower) as a “terrorist organization” creates massive legal complications. It would technically make any U.S. ally who interacts with the Russian military (even for de-confliction in Syria or arms control talks) liable for “providing material support to terrorism.”
    • Existing Tools: The U.S. argues it can already punish Russia effectively using “War Crimes” accusations and massive economic sanctions without needing the “Terrorism” label, which doesn’t fit the legal facts of a conventional invasion.

    Summary Table

    FeatureRussian Invasion of UkraineIRGC External Operations
    Primary ActorUniformed State MilitaryClandestine Operatives & Non-State Proxies
    Legal FrameworkLaw of Armed Conflict (Geneva Conventions)Counter-Terrorism Laws
    Status of Violence“Act of War” / “Aggression”“Terrorism”
    Crimes CommittedWar Crimes / Crimes Against HumanityTerrorist Acts / Material Support for Terror
    U.S. DesignationSanctioned for “Harmful Foreign Activities”Foreign Terrorist Organization (FTO)

    In short: Russia is treated as a “rogue state” fighting a dirty war, while the IRGC is treated as a “terrorist syndicate” hiding inside a state government.

    Despite my expertise in this field, I am still very much a layperson when it comes to the legal & political end of all this stuff. I hope you find these answers interesting and enlightening.

  • Here’s Wednesday’s designations, with some fixes to my understanding of the format (unlike other formats, the field name/label in OFAC listings are not really differentiated by formatting or separator character), as well as some reformatting so it’s easier on the eyes to tease apart the various sections, listings and fields:

    Venezuela-related Designations

    Treasury Press Release: Treasury Targets Oil Traders Engaged in Sanctions Evasion for Maduro Regime

    Additions:

    The following entities have been added to OFAC’s SDN List:

    [VENEZUELA-EO13850] – Executive Order 13850 – Blocking Property of Additional Persons Contributing to the Situation in Venezuela

    ARIES GLOBAL INVESTMENT LTD

    AKAs: ARIES GLOBAL INVESTMENT LIMITED

    • Address: Room 2611, 26th Floor, Southeast Technology R&D Center, 438, Jincheng Lu, Xiaoshan Qu, Hangzhou, Zhejiang, China
    • Address: Rm A 20/F ZJ 300, 300 LOCKHART RD, Wan Chai, Hong Kong, China
    • Identification Number: IMO 0052971
    • Registration Number: 76957722 (Hong Kong) issued 19 Aug 2024

    Based on the Treasury press release, this entity was designated for operating in the oil sector of the Venezuelan economy. It is the registered owner of the vessel DELLA, which has transported Venezuelan oil.

    CORNIOLA LIMITED

    AKAs: CORNIOLA LTD

    • Address: 149, Donggang Jiedao, Putuo Qu, Zhoushan, Zhejiang 316100, China
    • Address: Rm 909 G 9/F Hunghom Coml Ctr Twr A, 39 Ma Tau Wai Rd, Hunghom, Kowloon, Hong Kong, China
    • Identification Number: IMO 6434228
    • Registration Number: 75612503 (Hong Kong) issued 14 Aug 2023

    According to the Treasury press release, this entity was designated for operating in the oil sector of the Venezuelan economy. It is the registered owner of the vessel NORD STAR, which has transported Venezuelan oil.

    KRAPE MYRTLE CO LTD

    • Address: 149 Donggang Jiedao, Putuo Qu, Zhoushan, Zhejiang 316100, China
    • Address: Rm D5 5/F King Yip Fty Bldg, 59 King Yip St, Kwun Tong, Kowloon, Hong Kong, China
    • Identification Number: IMO 6342210
    • Registration Number: 74094750 (Hong Kong) issued 31 May 2022

    The Treasury press release states this entity acts as the ship manager and operator of the NORD STAR and was designated for operating in the oil sector of the Venezuelan economy.

    WINKY INTERNATIONAL LIMITED

    • Address: 14th Floor, Guangdong Investment Tower, 148 Connaught Road Central, Hong Kong, China
    • Address: Majuro, Ajeltake Island 96960, Marshall Islands
    • Organization Established Date: 01 Nov 2024
    • Registration Number: 128617 (Marshall Islands)

    Based on the Treasury press release, this entity was designated for operating in the oil sector of the Venezuelan economy. It is the registered owner of the vessel ROSALIND, which has transported Venezuelan oil.

    The following vessels have been added to OFAC’s SDN List:

    [VENEZUELA-EO13850] – Executive Order 13850 – Blocking Property of Additional Persons Contributing to the Situation in Venezuela

    DELLA (VRUB7)

    • Vessel Type: Crude Oil Tanker
    • Flag: Hong Kong
    • Other Vessel Flag: China
    • Vessel Year of Build: 2001
    • Vessel Registration Identification: IMO 9227479
    • MMSI: 477714500

    Linked to: ARIES GLOBAL INVESTMENT LTD

    The Treasury press release identifies this vessel as blocked property in which ARIES GLOBAL INVESTMENT LTDhas an interest. It has been used to transport Venezuelan oil.

    NORD STAR (3E7463)

    • Vessel Type: Crude Oil Tanker
    • Flag: Panama
    • Vessel Year of Build: 2006
    • Vessel Registration Identification: IMO 9323596
    • MMSI: 352003296

    Linked to: KRAPE MYRTLE CO LTD; CORNIOLA LIMITED

    According to the Treasury press release, this vessel is blocked property in which CORNIOLA LIMITED and KRAPE MYRTLE CO LTD have an interest. It has been used to transport Venezuelan oil.

    ROSALIND

    AKAs: LUNAR TIDE

    • Vessel Type: Oil Products Tanker
    • Flag: Guinea
    • Vessel Year of Build: 2004
    • Vessel Registration Identification: IMO 9277735

    Linked to: WINKY INTERNATIONAL LIMITED

    The Treasury press release identifies this vessel as blocked property in which WINKY INTERNATIONAL LIMITEDhas an interest. It has been used to transport Venezuelan oil.

    VALIANT (VRXH3)

    • Vessel Type: Crude Oil Tanker
    • Flag: Hong Kong
    • Other Vessel Flag: China
    • Vessel Year of Build: 2009
    • Vessel Registration Identification: IMO 9409247
    • MMSI: 477206500

    Linked to: ARIES GLOBAL INVESTMENT LTD

    Based on the Treasury press release, this vessel is identified as blocked property in which ARIES GLOBAL INVESTMENT LTD has an interest.

    So, this was a result of trial and error – and asking Gemini what went wrong a few times. I learned the following things:

    • Originally, Gemini added “Linked to” data to the entities, linking them to the vessels that linked back to them. I had to add a line to the prompt to tell it to report what was actually in the listing and not infer Linked to data
    • WordPress sometimes does not play nicely with Gemini without manual intervention:
      • Hyperlinks sometimes will be preserved, and sometimes will get lost. However, they work just fine outside a standard paragraph – like, in a heading block.
      • Certain formatting, like bolding and italics, are preserved in a WordPress paragraph – centering is definitely not. Originally, Gemini gave me the <center></center> HTML tags around the text I wanted centered. I had a handful of options – center the text manually, give up on the centering, make the line into a header line or use a Custom HTML block.
  • I’ve done a number of Gemini prompts where I’ve asked it to explain, with sources, various topics. And, not infrequently, after each piece of the response which has a corresponding source behind it, Gemini gives me a linkage symbol. And, when you copy and paste it into a blog post, those linkages become a series of numerical footnotes… without the cross-reference to the source. And some of these are duplicated (I asked it whether or not that was true).

    Do I really want to bore a non-expert with all of these? Do you really need to know that this snippet came from that source? Of course not – but I did want to make Gemini show its work.

    So, I came up with this:

    Instead of inserting citation markers throughout the response , provide a source list, including URLs in parentheses (as appropriate), at the end of the response. If multiple citations refer to the same base domain, refer to the base domain instead of the specific page.

    It may not be perfect, but it seems to work – I used it on that “nunation” post.

    If someone has better ideas, let me know. I’m sure there are equivalent terms to “base domain” – I certainly didn’t want to use “TLD”, although I’m sure I could have said “DNS address for the most specific common URL” or some such.

    Note: Gemini refers to these as source markers or citation markers. What other AI engines call them – or how they’re represented in responses – I can’t say. At some point, might I have a shootout with ChatGPT, CoPilot, Claude, etc? Sure… but not today.

    ,