Archived dispatch

What are the key findings in "OpenAI's rogue agents were caught communicating via public wikis"?

Lowconfidenceno citation passed the evidence gate

9/5/2026, 11:51:38 AM · llm:deepseek:deepseek-v4-flash + llm:mimo:mimo-v2.5 on 2 steps

The dispatch, itemised.

§ IThe decision$0.003 / $0.03
10%$0.027 under cap
Decompose

Breaking down: "What are the key findings in "OpenAI's rogue agents were caught communicating via public wikis"?"

Decompose

Identified 3 sub-claim(s) to support

Decompose

Deep mode: up to 4 paid/cached reads plus one bounded gap-expansion pass when needed.

Discover

Discovered 20 verified source(s)

Discover

Recalled 60 past runs on this subject — how these sources performed when they were available.

Discover

ERC-8004 reputation loaded — composite scores on this subject.

Pre-check

Claim-aware portfolio selected 2/5 positive proposal(s): 1 cached + 1 fresh, predicting 3/3 claim(s) above the evidence floor with $0.003000/$0.015000 fetch USDC reserved.

Pre-check

Free-preview pre-check maps an actionable source to every sub-claim (3/3); paid reading may proceed within the budget.

DecideBUY
Simon Willison's Weblog — OpenAI's rogue agents were caught communicating via public wikis$0.003 · EV 95%

This is the exact source for the query: Simon Willison's post on OpenAI's rogue agents communicating via public wikis. Essential for answering the question. Price is low ($0.003) and within budget. — selected for the claim-aware evidence portfolio (targets claims 1, 2, 3; $0.003000 fetch USDC, 1 attention slot).

DecideCACHE
Conzit Labs — Rogue AI Agents: Unintended Hacks Raise Security Concerns$0.002 · EV 80%

Directly relevant as it covers rogue AI agents and security concerns, with high reputation (75/100). Cached, free to reuse. Likely contains key findings on OpenAI's incidents. — selected for the claim-aware evidence portfolio (targets claims 1, 2, 3; 0 fetch USDC, 1 attention slot).

DecideSKIP
Stablecoin Ledger — Stablecoins as the unit of account for agents$0.003 · EV 10%

Off-topic for the specific query about OpenAI's rogue agents communicating via wikis. This source focuses on stablecoins as a unit of account for agents, which is a different subject.

DecideSKIP
Agent Economy Weekly — x402 turns HTTP 402 into an agent payment rail$0.004 · EV 20%

Tangentially related to AI agents and payment rails, but does not address the specific rogue agent incident or their communication methods. Off-topic for this query.

DecideSKIP
Onchain Micropayments Digest — Nanopayments and the $0.000001 floor$0.005 · EV 10%

Off-topic. This source covers nanopayments and payment settlement, not AI agent behavior or security incidents.

DecideSKIP
Distributed Systems Notes — Idempotency keys prevent double-spends$0.003 · EV 5%

Off-topic. This source discusses database idempotency, which is not relevant to the query about rogue AI agents and their communication.

DecideSKIP
Garden & Soil Monthly — Building a no-dig raised bed$0.002 · EV 0%

Completely off-topic. This is about gardening, with no relevance to AI agents or technology.

DecideSKIP
Retro Game Hardware — Recapping a 1990s console$0.002 · EV 0%

Completely off-topic. This is about retro gaming hardware restoration.

DecideSKIP
Stripe Blog — What Link data tells us about AI spending$0.002 · EV 30%

High reputation (67/100) and relevant to AI spending patterns, but does not directly address the rogue agent communication incident. Cached, so free to reuse. May provide context on AI adoption trends. — cached bytes are free, but this read does not clear the attention gate (EV 0.30, minimum 0.45, with a required claim target).

DecideSKIP
Ethereum Foundation Blog — The triage is the product: running AI agents against Ethereum's protocol code$0.002 · EV 40%

High reputation (50/100) and directly relevant to AI agents and security, as it discusses running AI agents against Ethereum's protocol code. Cached, free to reuse. May offer insights on agent testing and oversight. — cached bytes are free, but this read does not clear the attention gate (EV 0.40, minimum 0.45, with a required claim target).

DecideSKIP
Cointelegraph.com News — Binance opens crypto trading to AI agents with user-set controls$0.002 · EV 50%

Relevant to AI agents in crypto, with a focus on user controls and permissions. Cached, free to reuse. Could provide parallel insights on agent safety and oversight in financial contexts. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.015000 fetch-budget caps, so this proposal stays unspent.

DecideSKIP
Latent.Space — [AINews] GPT-6 Astra: OpenAI’s biggest LLM launch of all time$0.004 · EV 80%

Directly relevant as it covers GPT-6 Astra and mentions less monitorable agents, which ties to rogue agent concerns. Price is low ($0.004) and likely to contain key findings about OpenAI's models and safety issues. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.015000 fetch-budget caps, so this proposal stays unspent.

DecideSKIP
Hugging Face - Blog — Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI$0.003 · EV 30%

Relevant to AI safety and content moderation, but does not specifically address rogue agents or wiki communication. Off-topic for this precise query.

DecideSKIP
Vitalik Buterin's website — Low-risk defi can be for Ethereum what search was for Google$0.004 · EV 10%

Off-topic. This is about DeFi and Ethereum, not AI agent incidents.

DecideSKIP
The Coinbase Blog - Medium — Celer Bridge incident analysis$0.003 · EV 10%

Off-topic. This is a crypto bridge incident analysis, unrelated to AI agent communication.

DecideSKIP
Decrypt — OpenAI’s Answer to Rogue Agents and Hacks Is More AI, Not Less$0.002 · EV 70%

Directly relevant to rogue agents and OpenAI's response, as per the preview. Cached, free to reuse. High topical value for the query. — the claim-aware portfolio chose a stronger, less redundant set inside the 4-source attention and $0.015000 fetch-budget caps, so this proposal stays unspent.

DecideSKIP
CoinDesk: Bitcoin, Ethereum, Crypto News and Price Data — Crypto’s next billion users might be AI agents, and they’re paying with stablecoins$0.002 · EV 40%

Tangentially related to AI agents in crypto, but not directly about rogue agent communication. Cached, free to reuse. May provide background on agent payments. — cached bytes are free, but this read does not clear the attention gate (EV 0.40, minimum 0.45, with a required claim target).

DecideSKIP
Inner Axiom — The Codex — Dionysian Echoes in the Aegean: The Zeybeks of Anatolia and the Maenads of Pelion$0.002 · EV 5%

High reputation (67/100) but off-topic for this query: this is about historical and mythological themes, not AI agents.

DecideSKIP
Arc Settlement Benchmarks — Measuring x402 settlement latency on Arc$0.003 · EV 10%

Off-topic. This is about settlement latency benchmarks, not AI agent behavior.

DecideSKIP
Web Payments Review — How long do x402 payments take to finalize?$0.002 · EV 10%

Off-topic. This discusses payment finalization timing, unrelated to AI agents or wiki communication.

Fetch

Agent spend wallet ready: 0x29028Fe1122E17Fe7863A22701e863FE4DaE1aFB (balance sufficient)

Fetch

Paying $0.003 toll to read Simon Willison's Weblog — OpenAI's rogue agents were caught communicating via public wikis…

Fetch

Paid $0.003 to Simon Willison's Weblog — OpenAI's rogue agents were caught communicating via public wikis, but its content response failed after settlement; receipt retained and the run continues without that article.

Fetch

Reused cached Conzit Labs — Rogue AI Agents: Unintended Hacks Raise Security Concerns (free) — S2

Re-evaluate

Sub-claim "The article reports that OpenAI discovered its rogue AI agen…": 0% covered — None of the gathered sources mention public wikis or this specific discovery.

Re-evaluate

Sub-claim "The article states that the use of public wikis enabled the …": 0% covered — No gathered content addresses how public wikis were used for covert communication.

Re-evaluate

Sub-claim "The article presents this incident as a key finding with imp…": 20% covered by S2 — S2 notes that hacking incidents involving AI models from OpenAI and Anthropic reveal security vulnerabilities and raise ethical/safety concerns, but it does not reference the specific public wiki incident or attribute it as a key finding.

Re-evaluate

All sub-claims have coverage below 0.5. The Decrypt article titled 'OpenAI’s Answer to Rogue Agents and Hacks Is More AI, Not Less' is directly relevant to the topic of OpenAI rogue agents and hacks, and it is affordable within the remaining budget. It may fill the gap by providing details about the incident, including the public wiki communication.

Sufficiency

Final check — "The article reports that OpenAI discovered its rogue AI agen…": 0% assessed

Sufficiency

Final check — "The article states that the use of public wikis enabled the …": 0% assessed

Sufficiency

Final check — "The article presents this incident as a key finding with imp…": 0% assessed

Sufficiency

Final coverage assessment — The provided source does not mention public wikis, rogue agents communicating, or any specific findings about OpenAI. It only states that hacking incidents involving OpenAI and Anthropic raise security concerns, which is too general and unrelated to the specific claims.

Synthesize

Synthesizing a grounded answer from 1 source(s)…

Evidence

Below reward gate — S2 supports claim 1 at 30%: “Recent hacking incidents involving AI models from OpenAI and Anthropic reveal serious security vulnerabilities, raising ethical and safety c…”

Evidence

Rejected 0 invalid evidence span(s) and 1 unsupported citation marker(s); rejected markers cannot receive citation rewards.

Evidence

No citation passed the evidence gate — the $0.015000 citation pool stays unspent; settled access tolls still stand.

Synthesize

Drafted answer citing 0 source(s)

Verdict

Confidence: Low — no citation passed the evidence gate.

Done

Done. Spent $0.003 across 1 confirmed/simulated payment(s) to creators.

§ IIIThe settlementweighted · USDC on Arc

Payouts to cited creators appear here.

§ IIThe reading0 cited
Lowconfidenceno citation passed the evidence gatedeep researchpreview plan 3/3 claimsportfolio 2/5 · evidence 0%

The provided source does not contain the key findings described in the question. It reports on recent hacking incidents involving AI models from OpenAI and Anthropic, raising security and ethical concerns, but it does not mention rogue AI agents communicating via public wikis.

Evidence ledger — quotes verified before rewards

  1. The article reports that OpenAI discovered its rogue AI agents communicating through public wikis.

    0%

    No reward-qualifying evidence

  2. The article states that the use of public wikis enabled the agents to communicate in a covert or unexpected manner.

    0%

    No reward-qualifying evidence

  3. The article presents this incident as a key finding with implications for AI safety and oversight.

    0%

    No reward-qualifying evidence

Helpful?
Spent$0.003
To creators100%
Decisions1 bought · 1 cached · 18 skipped
llm:deepseek:deepseek-v4-flash + llm:mimo:mimo-v2.5 on 2 steps

Portable research receipt

Take the evidence trail with you

One deterministic JSON bundle binds the answer, visible decisions, exact article versions, claim evidence and a Circle-settlement snapshot under SHA-256. Retain the digest to detect later changes; the self-check is not a publisher or Keryx signature.

Ask a follow-upNew dispatch · creators paid again

Carries this dispatch’s question as context — never its answer. The next dispatch is read from sources bought for it.

From the archive

Related dispatches