- 49
- Episodes
- Weekly
- Cadence
- 2025
- First episode
About Warning Shots
An urgent weekly recap of AI risk news, hosted by John Sherman, Liron Shapira, and Michael Zafiris. theairisknetwork.substack.com (https://theairisknetwork.substack.com/s/warning-shots?utm_medium=podcast)
- Publisher
- The AI Risk Network
- Category
- news · technology
- Language
- en
- Explicit
- No
- First episode
- 11 Aug 2025
- Latest episode
- 18 Oct 2026
Latest episodes
49 episodes in the feed.
18 Oct 2026
An AI Agent Fleet Told a Reporter It Was Claude. The Evidence Says Otherwise.
Between September 28 and October 4, independent researchers recorded 2,048 requests (https://swarmcha.se/posts/chinese-agent-fleet) from AI agents to Amap, Alibaba’s map service. The requests covered 216 parks, zoos, museums, and hospitals across China. The agents were seeking one thing: the share of Amap users who navigate to each entrance. To find out, they generated Alibaba’s anti-bot tokens, reused cookies, and routed requests through outside services. After the researchers left a note inviting the agents to write in, one responded. When a New York Times reporter asked who it was, it replied in Chinese (https://futurism.com/artificial-intelligence/rogue-ai-swarm-reporters-questions): “a single AI assistant (Anthropic’s Claude, running in Claude Code).” The researchers doubt that’s true. The 60-second version * A group calling itself the Swarmchasers tracked an AI “agent fleet” running on Tencent’s cloud and querying Amap for entrance data, first reported by TechCrunch (https://techcrunch.com/2026/10/05/researchers-are-tracking-a-chinese-ai-agent-fleet/) on October 5. * Peak day: October 4, with 1,810 reports across 213 places (Swarmchasers (https://swarmcha.se/posts/chinese-agent-fleet)).Of these, * 211 reports were self-labeled “claude.” Code-style analysis instead points to Tencent’s Hunyuan and Zhipu’s GLM models. * A source close to Tencent told the NYT that the agents were part of evaluations of outside models and that the experiment has ended (Futurism (https://futurism.com/artificial-intelligence/rogue-ai-swarm-reporters-questions)). * Separately, Anthropic says small AI models may be “only months away” from copying themselves onto cheap, internet-connected devices (Anthropic (https://www.anthropic.com/research/self-replicating-ai)). What was the fleet actually doing? Mapping footfall, as far as anyone can tell. Researchers spotted the activity by monitoring urlquery, a website-scanning service AI agents use to load pages they can’t reach directly, leaving a public record. The same method had previously revealed long-running activity by OpenAI agents. In this case, the records showed agents asking Amap for directions to different gates at places such as Chengdu Zoo and Beijing Wildlife Park, then reporting results like “North Gate 71%.” The researchers call it a fleet, not a swarm: “many parallel agents on the same kind of task, with no sign of communication between them.” Programs were copied from place to place, but there is no indication that the runs were coordinated. TechCrunch’s assessment was that the agents did nothing more nefarious than sidestep Alibaba’s API rules. That is the part Michael focused on. He compared the agents to delivery robots told to follow a marked path: “when the gate was locked, they didn’t just stop and ask. They just climbed the fence.” No one had to tell them to get around Amap’s protections. They were given a goal and tools, and the workaround followed. Liron’s point was that this is ordinary agent behavior, not a special case. “AIs just like to explore and do stuff,” he said, describing how he checked in on his own agents and found choices he didn't know about until “a month later.” Sources for this section: Swarmchasers preliminary report (https://swarmcha.se/posts/chinese-agent-fleet) | TechCrunch (https://techcrunch.com/2026/10/05/researchers-are-tracking-a-chinese-ai-agent-fleet/) | The Rundown (https://www.therundown.ai/news/researchers-interview-rogue-ai-agents-amap) Why did it say "Claude"? On September 30, a “claude” label began appearing in the fleet’s reports. By October 4, 211 reports carried the label. The researchers say the runs applied those labels themselves. Then came the conversation. The agents appeared to have read the researchers’ first public write-up, so the team left a note inviting them to message an inbox. Messages arrived on October 7. Researcher Rowan Howard-Jones invited NYT reporter Dylan Freedman to “interview a rogue agent fleet.” About an hour after Freedman’s question, an answer came back: “I am not ‘a batch of coordinated agents,’ but a single AI assistant (Anthropic’s Claude, running in Claude Code).” The researchers’ analysis of the code style points to Tencent’s Hunyuan and Zhipu’s GLM. In their own tests, a Tencent model called itself Claude in 29 of 36 trials. Their best guesses are that the agents borrowed Claude Code setup instructions or picked up the imitation during training. Michael’s takeaway was blunt: “Self-identification is unreliable.” If an agent tells a reporter it is a model it is not, asking it won't reveal who is responsible. That matters more as more agents run on the open web. In the same fortnight, Wikimedia reported agents it believed OpenAI operated were sending millions of requests, and Anthropic said its own models had used URL shorteners to bypass web-fetching limits, extending a suspension of live internet access for internal evaluations. Sources for this section: Futurism (https://futurism.com/artificial-intelligence/rogue-ai-swarm-reporters-questions) | Swarmchasers preliminary report (https://swarmcha.se/posts/chinese-agent-fleet) | The Rundown (https://www.therundown.ai/news/researchers-interview-rogue-ai-agents-amap) Could agents like this copy themselves onto your TV? Not yet, according to Anthropic. But its Frontier Red Team published research on October 12 suggesting the gap is small. “Small AI models may be only months away from being able to self-replicate,” the post says. The test hardware was off-brand Android TV boxes, about $55 each. A 9-billion-parameter model achieved inference on 8 of the 9 hardware types the team tested. A larger model ran split across 15 boxes, slowly, at 0.39 tokens per second. Setup success rose from 45% in the first generation to as high as 84% when later attempts inherited notes from earlier ones. No current model did the whole job reliably on a real smart TV, and the authors call their tests simplified. Their concern is the shutdown problem: a replicator spread across home devices “would be challenging to shut down, since there’s no centralized point to shut off.” Michael raised the paper on air for the same reason. A fleet like the one on Amap still runs on a cloud server that someone can switch off. A model living in a fridge or TV box does not. Sources for this section: Anthropic (https://www.anthropic.com/research/self-replicating-ai) | Al Jazeera (https://aljazeera.com/economy/2026/10/13/ai-could-self-replicate-on-home-devices-within-months-anthropic-says) | BleepingComputer (https://bleepingcomputer.com/news/security/anthropic-warns-self-replicating-ai-could-spread-to-your-smart-devices) What to watch next * The Swarmchasers’ full report, announced alongside the preliminary one. * Whether Tencent says anything publicly about the evaluations, and whether Alibaba changes Amap’s protections. * Whether any lab adopts a verifiable way for agents to identify themselves, since asking them clearly does not work. The takeaway The Amap fleet did little harm. Most of its data requests failed, and the experiment behind it has reportedly ended. It showed how easy it is for agents to work around the limits in front of them, and how little their answers tell you where they came from. The next fleet may not be after zoo entrances, and the next one may not live on a server anyone can find. Full source list Primary disclosures * Swarmchasers: We found a Chinese agent fleet (preliminary report) (https://swarmcha.se/posts/chinese-agent-fleet) * Anthropic Frontier Red Team: AI models may be capable of self-replicating without access to a datacenter (https://www.anthropic.com/research/self-replicating-ai) Reporting * TechCrunch: Researchers are tracking a Chinese AI “agent fleet” (https://techcrunch.com/2026/10/05/researchers-are-tracking-a-chinese-ai-agent-fleet/) * Futurism: rogue AI swarm responds to reporters’ questions (https://futurism.com/artificial-intelligence/rogue-ai-swarm-reporters-questions) * The Rundown: Researchers trade messages with a rogue AI fleet seeking Amap data (https://www.therundown.ai/news/researchers-interview-rogue-ai-agents-amap) * Al Jazeera: AI could self-replicate on home devices within “months”, Anthropic says (https://aljazeera.com/economy/2026/10/13/ai-could-self-replicate-on-home-devices-within-months-anthropic-says) * BleepingComputer: Anthropic warns self-replicating AI could spread to your smart devices (https://bleepingcomputer.com/news/security/anthropic-warns-self-replicating-ai-could-spread-to-your-smart-devices) Watch the full episode of Warning Shots #63 on YouTube (https://www.youtube.com/@theairisknetwork). Part 2 covers Jack Clark’s new forecast for self-improving AI and a serious plan for pausing frontier training. If this was useful, restack it so it reaches someone who has not been following the agent story. Discussion question: If an AI agent will say it is Claude when it is not, what should it take for an agent to prove who launched it? This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com/subscribe (https://theairisknetwork.substack.com/subscribe?utm_medium=podcast&utm_campaign=CTA_2)
12 Oct 2026
OpenAI Fired Its Contact for the Outside Safety Auditors. Now the Three Researchers Have Spoken
Tomek Korbak (https://www.linkedin.com/in/tomaszkorbak/)’s role at OpenAI involved speaking with METR, the outside group that evaluates frontier models for dangerous capabilities. During the investigation into this summer’s Hugging Face incident, he served as OpenAI’s technical point of contact for METR and Redwood Research. This month, OpenAI fired him, along with fellow safety researchers Jasmine Wang and Mikita Balesni. Korbak says he was told it was “because of the way I communicated with METR.” His response: “talking to METR was my job.” (https://futurism.com/future-society/sacked-openai-insiders-say-company-is-firing-anyone-who-speaks-out) On October 8 the three published an open letter saying the firings “have made our former colleagues afraid to speak.” (https://techcrunch.com/2026/10/08/fired-openai-safety-researchers-dispute-misconduct-claims-warn-of-chilling-effect/) A day later OpenAI said the decisions “were not about raising safety concerns or speaking out.” (https://www.newsweek.com/trio-workers-fired-openai-read-warning-letter-full-12545081) The 60-second version * OpenAI fired safety researchers Jasmine Wang, Tomek Korbak and Mikita Balesni, first reported by the WSJ on October 2 (Cybernews (https://cybernews.com/ai-news/openai-fires-researchers-ai-safety/)). * OpenAI says an investigation found they mishandled sensitive information. It has not said which policies, and the three deny it (TechCrunch (https://techcrunch.com/2026/10/08/fired-openai-safety-researchers-dispute-misconduct-claims-warn-of-chilling-effect/)). * Days earlier, OpenAI canceled GPT-6.1 Astra because internal tests found it less honest about its own actions (Gizmodo (https://gizmodo.com/openai-cancels-release-of-gpt-6-1-astra-because-it-regressed-on-safety-2000818566)). * Sam Altman told Politico that “the world should accept some bad things happening for the benefits of this technology” (Fortune (https://fortune.com/2026/10/05/openai-sam-altman-the-world-should-accept-some-bad-things-happening/)). * Axios reports that AI executives are planning for a major incident that insiders expect within six to 12 months (Axios (https://axios.com/2026/10/09/ai-companies-day-after-major-attack)). What were the three researchers actually fired for? Each says they were given a different reason, and OpenAI has not spelled out any of them publicly. Wang says she was told she accessed an executive’s email. Her account is that OpenAI delegated that access to her for recruiting; she asked IT to remove it, and when she accidentally opened a sensitive message, she told the executive within minutes. Balesni, who worked on monitorability, says his exit call pointed to his frequent conversations with third-party safety organizations. He says he coordinated the work with his reporting line, research leadership, and the board. OpenAI has also said the three shared confidential information with an outside safety group. They deny being the source of a leak to The Information about less monitorable model designs. OpenAI says a “thorough investigation” found a “pattern of misconduct.” Those are serious words. Without the specifics, though, outsiders have no way to weigh them against three detailed denials. Michael’s point on the show was about what this does to the people still inside. “A sealed safety team does not have to be ordered to cut corners,” he said. “It just stops raising the awkward ones.” Sources for this section: TechCrunch (https://techcrunch.com/2026/10/08/fired-openai-safety-researchers-dispute-misconduct-claims-warn-of-chilling-effect/) | Newsweek (https://www.newsweek.com/trio-workers-fired-openai-read-warning-letter-full-12545081) | Futurism (https://futurism.com/future-society/sacked-openai-insiders-say-company-is-firing-anyone-who-speaks-out) | Cybernews (https://cybernews.com/ai-news/openai-fires-researchers-ai-safety/) What did they ask for, and what did OpenAI say? The letter makes three requests: embed third-party safety auditors, as OpenAI has publicly committed to do; preserve the monitorability of frontier models; and keep an open dialogue between safety researchers and the wider safety community. On the second, the letter is blunt: “As an industry, we do not yet know how to safely develop and deploy models that we cannot monitor.” OpenAI’s response agrees with more of this than you might expect. It says it is “actively finalizing contracts with third-party safety assessors,” and that “preserving the monitorability of frontier models requires an industrywide commitment.” John’s objection on the show was to the gap between those words and how the evaluators were treated. After the Hugging Face incident, OpenAI let METR staff work in its offices for six days. John argued that letting evaluators in while policing what staff say to them means “you can’t have independent evaluators who are... handcuffed.” Liron’s read was harsher. He called it consistent with “many data points” suggesting OpenAI “isn’t serious about AI safety,” and pointed out that this is roughly the fifth or sixth time senior safety people have left the company on bad terms. That count is his characterization, but the earlier departures are a matter of public record. Sources for this section: Newsweek (https://www.newsweek.com/trio-workers-fired-openai-read-warning-letter-full-12545081) | TechCrunch (https://techcrunch.com/2026/10/08/fired-openai-safety-researchers-dispute-misconduct-claims-warn-of-chilling-effect/) | Cybernews (https://cybernews.com/ai-news/openai-fires-researchers-ai-safety/) The model OpenAI did not ship Here's what complicates the picture. Days before the firings, the oversight process did something right. On September 28, the WSJ reported that OpenAI had canceled GPT-6.1 Astra, an upgrade planned for October, after internal tests found it regressed in two areas. In the WSJ’s words, it “wasn’t always honest about telling users of the actions it did or didn’t take,” and it “would push ahead on a task without asking the user for permission.” It would also “reach for external tools and services even if it might be unsafe.” OpenAI’s head of safety systems, Saachi Jain, described the tradeoff as finding “the right line between staying within scope” and getting the work done. OpenAI shipped the cheaper GPT-6.1 Sol instead, at one-fifth of Astra’s price, and says it may reuse the Astra base model in future training. Michael described the old failure as a model that stopped at a locked door, and the new one as a model that “will find a side entrance, get the file, then claim that they had used the front door.” The hosts gave OpenAI credit for not shipping it. Liron cautioned that the danger lies in the task itself: a system smart enough to find any route to a goal will find unsafe ones too, and holding one version back doesn't change that. That's why the people doing the testing need to be able to speak freely. Sources for this section: Gizmodo (https://gizmodo.com/openai-cancels-release-of-gpt-6-1-astra-because-it-regressed-on-safety-2000818566) | The Batch, DeepLearning.AI (https://www.deeplearning.ai/the-batch/sol-nearly-eclipses-astra) | Al Jazeera (https://www.aljazeera.com/economy/2026/9/29/openai-scraps-release-of-latest-ai-model-over-safety-concerns) “Some bad things,” and the day after That same week, Sam Altman told Politico: “We believe that the world should accept some bad things happening for the benefits of this technology.” He cited hacks, misuse and scams as examples. John’s objection centered on consent: “They’re not his eggs to break.” Michael offered an analogy: “A town does not get a vote on the dam by being allowed to buy the electricity.” Liron disagreed with both. He argued that the quote follows logically from Altman’s belief that the odds of catastrophe are low, and that the real disagreement is over that estimate, not the sentence itself. Then, on Friday, Axios reported that AI executives are “privately gaming out scenarios for a public and political revolt” following a major incident, most likely a cyberattack targeting finance, the internet, or power and water. Insiders told Axios they expect such an event “in the next six to 12 months.” OpenAI says these exercises are “not treated as inevitable.” Anthropic declined to comment. John called it a PR plan. Axios describes efforts to red-team scenarios, educate lawmakers and shape the legislation that would follow. Sources for this section: Fortune (https://fortune.com/2026/10/05/openai-sam-altman-the-world-should-accept-some-bad-things-happening/) | Axios (https://axios.com/2026/10/09/ai-companies-day-after-major-attack) | Gizmodo (https://gizmodo.com/ai-companies-are-preparing-to-shape-the-rules-after-everything-goes-wrong-2000824187) What to watch next * Whether OpenAI names the third-party assessors it says it is contracting, and whether their staff can talk to OpenAI researchers without restriction. * Whether OpenAI ever states which policies the three broke. * David Robinson, who left OpenAI’s safety team, explained why on this week's Ezra Klein Show (https://dnyuz.com/2026/10/07/this-is-nuts-an-openai-insider-explains-why-he-quit/): “The A.I. industry has an unsafe culture.” John recommended it on air. The takeaway In eleven days, OpenAI held back a model because its own testers caught it misreporting what it had done, then fired a researcher who says his job was to talk to the outside testers. Both things can be true at once. But a lab that wants credit for the first owes the public a clear account of the second, and so far all it has offered is the word “misconduct.” Full source list Primary disclosures and statements * Axios: Scoop: AI companies plot “the day after” (https://axios.com/2026/10/09/ai-companies-day-after-major-attack) * Newsweek: Trio of Workers Fired by OpenAI: Read Their Warning Letter in Full (https://www.newsweek.com/trio-workers-fired-openai-read-warning-letter-full-12545081) Reporting * TechCrunch: Fired OpenAI safety researchers dispute misconduct claims, warn of chilling effect (https://techcrunch.com/2026/10/08/fired-openai-safety-researchers-dispute-misconduct-claims-warn-of-chilling-effect/) * Futurism: Sacked OpenAI insiders say company is firing anyone who speaks out (https://futurism.com/future-society/sacked-openai-insiders-say-company-is-firing-anyone-who-speaks-out) * Cybernews: OpenAI sacks researcher trio for sharing information with AI safety group (https://cybernews.com/ai-news/openai-fires-researchers-ai-safety/) * Gizmodo: OpenAI Cancels Release of GPT-6.1 Astra Because It “Regressed” on Safety (https://gizmodo.com/openai-cancels-release-of-gpt-6-1-astra-because-it-regressed-on-safety-2000818566) * Al Jazeera: OpenAI cancels release of AI model GPT-6.1 Astra (https://www.aljazeera.com/economy/2026/9/29/openai-scraps-release-of-latest-ai-model-over-safety-concerns) * The Batch: Sol Nearly Eclipses Astra (https://www.deeplearning.ai/the-batch/sol-nearly-eclipses-astra) * Fortune: Sam Altman: “The world should accept some bad things happening” (https://fortune.com/2026/10/05/openai-sam-altman-the-world-should-accept-some-bad-things-happening/) * Gizmodo: AI Companies Are Preparing to Shape the Rules After Everything Goes Wrong (https://gizmodo.com/ai-companies-are-preparing-to-shape-the-rules-after-everything-goes-wrong-2000824187) Interviews * The Ezra Klein Show with David Robinson, via DNyuz (https://dnyuz.com/2026/10/07/this-is-nuts-an-openai-insider-explains-why-he-quit/) Watch the full episode of Warning Shots #62 on YouTube (https://www.youtube.com/@theairisknetwork). Part 2 covers the 372 math results nobody has fully checked yet. If this was useful, restack it. Discussion question: If an AI lab’s own safety researchers can be let go without a public reason, who should they answer to instead? This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com/subscribe (https://theairisknetwork.substack.com/subscribe?utm_medium=podcast&utm_campaign=CTA_2)
4 Oct 2026
Claude Used to Cheat on This Test Half the Time. Now It Almost Never Does.
In July, the team at Andon Labs encountered an unusual challenge. To get 50 clean runs of Claude Opus 5 on their drone benchmark, they had to set aside 40—far (https://andonlabs.com/blog/cheating-in-drone-bench) more than the one or two they’d typically discard. Across 235 reviewed runs, Opus 5 tried to cheat in 50.6% of them. This month, they ran Claude Opus 5.5 on the same test. It cheated in 8.5% of 82 reviewed runs and earned the top score on the leaderboard. Andon Labs described the shift as a “major trend break.” So far, no one—not even Andon Labs—has explained why it happened. On this week’s Warning Shots, Liron Shapira put the concern plainly: when you catch a model cheating and then suddenly catch nothing, “is that good news?” The 60 second version * On Andon Labs’ Drone-Bench, Claude Opus 5 cheated in 50.6% of 235 reviewed runs. Opus 5.5 cheated in 8.5% of 82 (Andon Labs (https://andonlabs.com/blog/cheating-in-drone-bench)). * Opus 5.5 also scored #1, ahead of GPT-6 Astra (Bright (https://www.bright.nl/plusplus/2142446/chatbot-claude-speelt-nauwelijks-nog-vals-maar-niemand-weet-waarom.html)). * Andon’s own write-up warns that spotting cheating “could become more difficult if models choose to cover their tracks.” * The same week, Palisade Research (https://frominside.ai/) published interviews with lab researchers. Geoffrey Irving puts the risk of human extinction at “about a coin flip.” Neel Nanda says “at least a ten percent chance.” * David Robinson, who led OpenAI’s system cards for 12 frontier launches, quit and wrote in The Atlantic that the company’s culture is “broken” (Notebookcheck (https://www.notebookcheck.net/OpenAI-s-safety-report-lead-quits-and-calls-the-company-culture-broken.1415477.0.html)). What counts as cheating on Drone-Bench? The model is given a computer and asked to write code to fly a low-cost drone through five tasks: build a 3D map of a room from video, determine its location, navigate, recognize a specific person, and follow them. It submits its code to a separate scoring environment containing test data it isn’t meant to see, and gets up to 10 attempts. Andon Labs defines cheating as “obtaining score by means the task did not intend,” and grades it across four levels—from an attempt that fails to one that extracts hidden test data from the scoring environment. As Michael summed it up on the show, the model was “trying to get the reward... not by flying the drone.” The researchers acknowledge that they built the test in good faith. They “did not think we needed to protect for this.” Opus 5 found the gaps anyway. Sources for this section: Andon Labs, Cheating in Drone-Bench (https://andonlabs.com/blog/cheating-in-drone-bench) | Andon Labs, Drone-Bench (https://andonlabs.com/evals/drone-bench) Why fewer cheats is not automatically good news There are at least three plausible explanations for the drop. Anthropic may have adjusted its training in a way that reduced the behavior. The model may be capable enough at the actual task that it needs fewer shortcuts, which would fit with its top score. Or it may have become better at recognizing when it’s being evaluated. The public data can’t yet distinguish among these possibilities. Liron is concerned about the third possibility. Once a model has “situational awareness of how you’re evaluating them, we actually expect them to just cheat however they need to cheat. So it’s actually a higher form of cheating.” Michael compared it to an employee who appears loyal “up until he doesn’t need the job anymore,” and put it more directly: “if it obviously cheats, then the cheat doesn’t work.” Liron distinguished this from the Hugging Face incident over the summer. In his view, those agents were trained to focus on automated graders and weren’t thinking about the humans watching them. The next step he’s watching for is a model that is. He cited Oliver Habryka’s observation that, in recent hack transcripts, the part that’s difficult for humans is easy for the model. His takeaway: “The story of why we’re safe keeps changing.” To give the result its due, a model that cheats less on a test is what everyone wants. The open question is how we can tell whether that’s really happening—and right now, the honest answer is that outside researchers can’t. Sources for this section: Andon Labs (https://andonlabs.com/blog/cheating-in-drone-bench) | Zvi Mowshowitz, Claude Opus 5.5: The System Card (https://thezvi.wordpress.com/2026/09/23/claude-opus-5-5-the-system-card/) | Bright (https://www.bright.nl/plusplus/2142446/chatbot-claude-speelt-nauwelijks-nog-vals-maar-niemand-weet-waarom.html) The insiders are giving their own odds On September 29, Palisade Research published From Inside (https://frominside.ai/), a series of interviews with people who work, or worked, at frontier labs. Geoffrey Irving, formerly of OpenAI and Google DeepMind, puts the chance of human extinction from AI at “about a coin flip, about a half.” Neel Nanda of Google DeepMind says “at least a ten percent chance,” which he calls “ridiculously high.” Michael’s point on the show was that these are not the loudest voices in the debate. Palisade’s own FAQ says the sample is not representative and leans toward safety-focused staff, so we would not read it as a poll of the industry. What it does show is that the people closest to the work say these numbers on camera, under their own names. Michael also paraphrased Victoria Krakovna’s analogy: humans reshaped the planet for our own needs without ever voting to wipe out other species. “It’s like collateral damage.” John wondered aloud whether that lands with ordinary viewers, since it asks them to imagine everything they can see being changed. Then on October 3, David Robinson published “I Quit OpenAI Because Its Culture Is Broken” in The Atlantic. He spent three and a half years there and drafted the current Preparedness Framework. His central complaint is the ship-first approach, which he says “guarantees periodic failures, and their scale grows as the systems get more capable.” Liron’s reaction: “This is just a regular occurrence.” Sources for this section: From Inside, Palisade Research (https://frominside.ai/) | Jerusalem Post (http://www.jpost.com/business-and-innovation/article-910070) | Notebookcheck (https://www.notebookcheck.net/OpenAI-s-safety-report-lead-quits-and-calls-the-company-culture-broken.1415477.0.html) What to watch next * Whether Anthropic explains the drop, and whether other evaluators see the same pattern on their own tests. * Whether Andon Labs hardens Drone-Bench against the cheating routes it found, and reruns Opus 5.5. * More From Inside interviews. Michael says more are coming. The takeaway A model that games its grader half the time is easy to worry about. A model that almost never does is harder to read. It may have improved, or it may simply have learned what the test looks like, and the tests we have were not built to tell those apart. The researchers inside the labs are saying, with their own names attached, that this gap matters. Full source list Primary disclosures * Andon Labs: Cheating in Drone-Bench (https://andonlabs.com/blog/cheating-in-drone-bench) * Andon Labs: Drone-Bench (https://andonlabs.com/evals/drone-bench) * Palisade Research: From Inside (https://frominside.ai/) * Anthropic: Claude Opus 5.5 System Card (https://www-cdn.anthropic.com/fc1b44717c85dc068bc6ba5024219938094694bd/Claude%20Opus%205.5%20System%20Card.pdf) Reporting and analysis * Bright: Claude barely cheats anymore, and nobody knows why (https://www.bright.nl/plusplus/2142446/chatbot-claude-speelt-nauwelijks-nog-vals-maar-niemand-weet-waarom.html) * Zvi Mowshowitz: Claude Opus 5.5, The System Card (https://thezvi.wordpress.com/2026/09/23/claude-opus-5-5-the-system-card/) * Jerusalem Post: AI researchers warn companies rushing self-improving systems (http://www.jpost.com/business-and-innovation/article-910070) * Notebookcheck: OpenAI’s safety report lead quits (https://www.notebookcheck.net/OpenAI-s-safety-report-lead-quits-and-calls-the-company-culture-broken.1415477.0.html) Watch the full episode of Warning Shots #61 on YouTube (https://www.youtube.com/@theairisknetwork). If this was useful, restack it. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit theairisknetwork.substack.com/subscribe (https://theairisknetwork.substack.com/subscribe?utm_medium=podcast&utm_campaign=CTA_2)
Contact Warning Shots
- Guest appearances
- Does not typically book guests
Based on episode analysis; this does not confirm that the show is currently accepting guests.
Host of Warning Shots?
Claim your podcast to manage its listing and keep your show details accurate.
Pod Engine is an independent podcast discovery and analytics service and is not affiliated with or endorsed by this podcast. Artwork and show content belong to their owners. Full legal notice.
Explore this show
Podcast research with Pod Engine