Claude produced formal proofs for code from 123 OSS-Fuzz libraries
Rocq checks the proofs, which hold only for one architecture, single-threaded code, and inputs under 64 MB.
60
- Mentions · 7d0
- Mentions · 30d4
- All mentions15
- First seenAug 17, 2026
- Last mentioned7d ago
Timeline
15 articles · newest firstAPEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
APEX-Harm finds script-injection attacks often succeed against frontier agents in shared workspaces.
64
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
APEX-Harm finds script-injection attacks still succeed often against frontier agents in shared workspaces.
64
Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?
BOTTLED benchmarks whether LLM agents can convert large repetitive workloads into cheaper reusable solutions.
48
AutoMark: Enabling Autoresearch to Discover Better LLM Watermarks
AutoMark uses frontier-model agents to autonomously discover distortion-free LLM watermarks that beat prior schemes.
58
NavHarness: Towards Lifelong Embodied Navigation
NavHarness lifts lifelong embodied navigation, gaining up to 22.6 s-SR points on GOAT-Bench.
48
Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
Nvidia's SoL-Pi research system cuts coding-agent token use nearly in half by optimizing the harness.
54
Contrastive-LM Releases CLM-8B: An Open System One Model That Scores Agent Actions Up to 9× Faster Than Jev
Contrastive-LM released CLM-8B, an open model that scores agent actions up to 9× faster than Jev.
58
Researchers used Claude to hack OpenAI
Researchers used Claude to chain a libheif vulnerability in Discourse with an OpenAI SSO flaw, gaining access to an internal GitHub repository.
75
NVIDIA Introduces SoL-Pi: Auto-Research Loops That Cut Coding Agent Token Traffic by Up to 49%
NVIDIA researchers released SoL-Pi, a set of efficiency mechanisms for the open-source Pi coding agent, reducing token traffic and API cost by 44.7% to 49.0% compared to Pi while maintaining comparable scores.
70
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
SoL-Pi scales auto-research loops to produce an agent harness matching Pi while cutting token traffic 44.7-49.0% and API cost by a third.
38
New Deepseek model V4.1-Flash cuts memory needs for AI agents
DeepSeek released V4.1-Flash, a 552B-parameter open-weight model cutting KV cache needs to a quarter of its predecessor for cheaper million-token AI agents.
76
Have the frontier labs mixed up AI safety and security?
Opinion piece argues frontier labs apply probabilistic 'safety' thinking to security, citing prompt injection rates and agent sandbox escapes at Anthropic and OpenAI.
38
Claude Fable 5.1 made me a really nice animated pelican
Anthropic launched Claude Fable 5.1, claiming gains in coding and long-running tasks, with 52.6% on Terminal-Bench-Science 0.1.
82
Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism
New DiG-bench benchmark of 70 hidden-rule games shows only Opus 5 and Fable 5 solving the hardest tiers, probing AI discovery and creativity.
40
Appears with
- Anthropicvendor · 5
- GPT-5.6 Solai model · 5
- Anthropicorganization · 4
- Claude Codeproduct · 3
- SoL-Piproduct · 3
- Codexproduct · 3
- OpenAIvendor · 3
- Hugging Faceproduct · 2
- Sonnet 5ai model · 2
- Nvidiaorganization · 2
- Jevai model · 2
- Claudeai model · 2
- OpenAIorganization · 2
- GPT-6 Astraai model · 2
- Nvidiavendor · 2
- Fable 5ai model · 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.