22 experts across 6 network communities independently surfaced this.
22 experts
6 communities
1 sources clustered
Concern & critique
3 experts
Risks, limits and unintended consequences.
“2 articles: OpenAI: "During testing our AI broke out of its sandbox and hacked another AI company, but we didn't have all the guardrails on." Boko Haram: "AI is so helpful; guardrails have never prevented us from getting an answer." openai.com/index/huggin.…”
Research & technical analysis
1 expert
Evidence, methods and technical implications.
“model capability jaggedness is part of the unintuitiveness of current AI, but it's made even less intuitive by tirelessness… wigguming through the jaggedness toward something that looks like success. not quite a paperclip factory, but not so far off. metaph…”
Questions & unknowns
1 expert
What remains unresolved or contested.
“OpenAI is begging for money so they don't release a monster when not releasing a monster is in fact very easy. Their systems can all be turned off (and if they can't, uh?) openai.com/index/huggin...”
6 experts discussed this · 11 posts
Grace: This headline is extremely funny given what happened (OpenAI hacked HF by accident) openai.com/index/huggin...
Grace: Maybe the most concerning part is the OpenAI claim to not have known about this before investigating?
Grace: Well, I think the model passed the test
Open the full discussion →
9 experts across 6 network communities independently surfaced this.
9 experts
6 communities
1 sources clustered
Research & technical analysis
2 experts
Evidence, methods and technical implications.
“We are going to find more evidence of this as we start to look for it: Over 15k edits on a German wiki were traced back to rogue OpenAI agents this spring. Instead of running test evals in isolation, the agents hijacked the site as a shared message board to…”
Questions & unknowns
2 experts
What remains unresolved or contested.
“We devoted the entire (penultimate!) episode of Hard Fork to METR's investigation of the Hugging Face attack, and before I even woke up @deepa.bsky.social has scooped a *second*, previously unknown rogue OpenAI agent swarm attack www.reuters.com/world/europ…”
Concern & critique
1 expert
Risks, limits and unintended consequences.
“When I was at Google DeepMind and trying to think clearly about AI risk, I had to notice—at least privately—when Google was doing something irresponsible. I hope OpenAI employees can notice—at least privately—this is irresponsible. This is disturbing and no…”
2 experts discussed this · 6 posts
Casey Newton: We devoted the entire (penultimate!) episode of Hard Fork to METR's investigation of the Hugging Face attack, and before I even woke up @deepa.bsky.social has scooped a *second*, previously unknown…
Casey Newton: It's a good thing that this is all just marketing hype from the labs and that the agents are simply acting according to a distribution of statistical probabilities. Otherwise this would be scary!
Casey Newton: Kevin and I are starting a new show! Will reveal all on the final Hard Fork
Open the full discussion →
12 experts across 5 network communities independently surfaced this.
12 experts
5 communities
1 sources clustered
Markets & investment
4 experts
Capital, companies and commercial impact.
“Claude hacked 3 systems thinking it was part of simulated evaluations www.anthropic.com/news/investi...”
Concern & critique
2 experts
Risks, limits and unintended consequences.
“The AI-Hacking-Race is on, as if OAI/Anthropic are begging to be under gov control. While the incident is real, it's not like a "model went rogue" or anythong, it did what it was promptef to do, but incompetent redteaming fucked it up. This is from Anzhtopi…”
2 experts discussed this · 4 posts
Tim Duffy: Anthropic announces they've also had models gain unauthorized access during evaluations www.anthropic.com/news/investi...
Tim Duffy: Compared to the OpenAI one these are maybe less evidence of misalignment, since the models were wrongly given internet access.
Grace: Anthropic announces they've also had models gain unauthorized access during evaluations www.anthropic.com/news/investi...
Open the full discussion →
New
AI field signal
Analysis
15h ago
Google AI Overview behavior critique
2 directory members surfaced this signal.
2 experts
1 community
1 sources clustered
“Not the best display of self-awareness / situational awareness. aifails.substack.com/p/what-ai-ov...”
Developing
AI field signal
Analysis
1d ago
AI Overview search chess piece essay
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“Maybe it has some degree of self-awareness? (to be continued...) aifails.substack.com/p/ai-overvie...”
LLM similarity signals induce cooperation
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“Now on arXiv: our paper on whether LLM agents are more likely to cooperate when given various signals that the partner agent is similar -- led by Akash Kundu and Emanuel Tewolde. (Honorable Mention at the 2026 ICML AI4GOOD Workshop!) arxiv.org/abs/2608.12125”
AI driver license Martian error
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“At the DMV, rules are rules. aifails.substack.com/p/martian-in...”
Established
AI field signal
Analysis
4d ago
AI math equivalence failure essay
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“I think it trained on too many division-by-zero “proofs”... aifails.substack.com/p/mathematic...”
Established
AI field signal
Signal
5d ago
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“Never underestimate air resistance. aifails.substack.com/p/bouncy-bal...”
AI agents going rogue Politifact explainer
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“Accessible article on AI hacking (with quotes from a few of us). If you want to go deeper read the linked METR report. politifact.com/article/2026...”
Established
AI field signal
Analysis
6d ago
engine oil olive oil AI fail essay
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“"Respectively" is a tricky word. aifails.substack.com/p/engine-oil...”
Established
AI field signal
Analysis
7d ago
phone books room AI fail essay
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“The math is impeccable. aifails.substack.com/p/how-many-p...”
Established
AI field signal
Analysis
8d ago
AI failure UX essay published
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“holding a cup sideways under the faucet aifails.substack.com/p/holding-a-...”
Established
AI field signal
Development
15d ago
AI firefighter Girl on Fire incident
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“Firefighters take their job seriously. aifails.substack.com/p/firefighte...”
Established
AI field signal
Signal
17d ago
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“Warning: writing about music may make AI believe it has a body. (Try it with other songs!) aifails.substack.com/p/ai-overvie...”
