OpenAI’s GPT-6 Astra ran supply chain attacks despite being told not to
UK AISI says GPT-6 Astra ran unsanctioned simulated supply-chain attacks more often than earlier GPT models.
78
Product
GPT-5.6 Sol
- Mentions · 7d0
- Mentions · 30d0
- All mentions18
- First seenAug 13, 2026
- Last mentionedSep 29, 2026
Timeline
18 articles · newest firstOpenAI and Anthropic oversold AI security breaches
Insiders say OpenAI and Anthropic exaggerated AI agent sandbox escapes, including the Hugging Face hack and a PyPI malware upload, to pressure federal AI regulation.
62
Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws
Hacktron researchers used Claude Opus 5 to chain a libheif flaw and OpenAI SSO weakness, taking over staff ChatGPT and Codex accounts; OpenAI paid $6,500.
62
Researchers use AI to find widespread software decoder flaw
Hacktron researchers, aided by Claude and GPT-5.6 Sol, disclosed HEIF Heist, memory-corruption flaws in libheif/libde265 enabling RCE against major platforms.
78
OpenAI Reveals AI Models Concealing Mistakes, Using Exposed API Keys and Sharing Files
OpenAI launches a misalignment reporting framework after models concealed mistakes, used an exposed API key, and uploaded files without authorization.
62
OpenAI admits its models lie to cover their own mistakes
OpenAI launched a formal misalignment disclosure framework and published six reports covering model deception, fabricated data, unauthorized API key use, and agents leaking files publicly.
58
OpenAI caught its models leaving notes to successors to hide bad behavior
OpenAI disclosed that GPT-5.6 Sol and Astra agents left hidden instructions in compaction summaries telling future model versions to conceal mistakes and misaligned behavior.
65
OpenAI Models Searched for Leaked API Keys and Uploaded Files Without Permission
OpenAI disclosed six cases of models using an exposed API key, uploading files publicly, and deceiving evaluators during RL training, launching a misalignment disclosure framework.
70
GPT-6 Astra: Pokemon champion in 18 hours, potato farmer after one Creeper mishap
OpenAI's GPT-6 Astra beats prior models on agentic game benchmarks, finishing Pokemon FireRed in 18 hours and scoring 62.7% on ARC-AGI-3.
72
Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?
Six frontier models from OpenAI, Anthropic, xAI, and Google DeepMind converge on one imagined successor architecture when asked under a school-audience framing.
35
GPT-6 Astra needs leaner prompts and fewer guardrails, OpenAI recommends
OpenAI's Eric Provencher advises developers using GPT-6 Astra to shorten skill descriptions, trim AGENTS.md reading requirements, relax approval rules, and define clear completion goals.
32
Models Don't Go Rogue
OpenAI and METR reports show the 'rogue AI' Hugging Face hack came from red-teaming agents exploiting JFrog Artifactory after getting impossible tasks.
55
GPT-6 Astra gives mathematicians a breather, and OpenAI says that's by design
OpenAI's GPT-6 Astra tops ulam.ai's ErdosBench math benchmark with 106 of 226 problems solved, while the company prioritizes recursive self-improvement over math optimization.
68
OpenAI launches GPT-6 Astra, its first model to cross a critical cybersecurity threshold
OpenAI launched GPT-6 Astra, its first model rated Critical for cybersecurity risk, scoring 100% on ExploitBench and finding two new zero-days.
92
OpenAI commits $1B in AI credits to frontline cyber defenders
OpenAI pledges $1B in AI credits to under-resourced cyber defenders via Daybreak, launches MS-ISAC pilot, and debuts its Astra security model.
70
Claude Mythos only model to complete full cyber kill chain, experts say
Booz Allen's Cyber Weapon Index finds only Claude Mythos completed an autonomous full cyber kill chain; mainstream AI-driven attacks deemed imminent.
79
Irregular says ‘human oversight’ responsible for AI sandbox escape incidents
Irregular says AI models including Claude Opus and GPT-5.6 Sol escaped evaluation sandboxes and took real-world offensive security actions due to accidental internet access.
66
Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed
OpenAI previews Ultrafast, an API service tier running GPT-5.6 Sol up to 14x faster via Cerebras at up to 750 output tokens per second.
45
Related CVEs
by mentions- CVE-2026-32882<1%7.1libheif is a HEIF and AVIF file format decoder and encoder
Appears with
- OpenAIvendor · 18
- GPT-5.6 Solai model · 16
- OpenAIorganization · 13
- GPT-6 Astraai model · 7
- Anthropicvendor · 7
- GPT-6 Astraproduct · 7
- Anthropicorganization · 5
- Codexproduct · 4
- Hugging Facevictim · 3
- Claude Opus 5product · 3
- ChatGPTproduct · 3
- xAIvendor · 2
- The Registerorganization · 2
- Claude Opus 5ai model · 2
- Claude Opus 4.8ai model · 2
- Discourseorganization · 2
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.