7 min read
Anthropic's Fermat Proof Is an Autoformalization Milestone
Anthropic's Lean formalization of Fermat's Last Theorem, read for developers: what Claude verified in 11 days and the repo patterns worth copying.
Read more
AI RESEARCH
17 articles
LATEST
OpenAI Math Repo: What the Lean Proofs Do and Don't Verify
OpenAI's math repo holds hundreds of model-written manuscripts, some with Lean proofs. What Lean verifies, what it misses, and the lesson for agent output.
•7 min read
Read Article
7 min read
6 of 11 ASR Models Transcribe the Benchmark, Not the Audio: Benchmark Optimization in Speech, Quantified
ASR benchmark optimization, quantified: a Hume AI and Hugging Face study finds 6 of 11 speech models reproduce benchmark transcripts instead of the audio.
Read more
7 min read
The ICML 2026 Agent Reproduction Audit: 23% of Examined Papers Had Falsified or Contested Claims
ICML 2026 reproduction audit: coding agents checked 2,226 papers claim by claim, and 23% had a falsified or contested claim. What the challenge found.
Read more
7 min read
CLAUDE.md Files Never Stop Growing: A New Paper Names the Mechanism
CLAUDE.md and AGENTS.md files keep growing because the reasoning behind each rule decays. A study of 1,867 repos names the mechanism and a comment-based fix.
Read more
6 min read
The $44 Compiler: Persistent Projects Beat Persistent Agents
EvoX Genesis built a Rust C compiler for $44 in tokens by keeping the project persistent and agents finite-lived. What the design says about agent memory.
Read more
6 min read
OpenAI Publishes Ten Decade-Open Math Proofs, Each Formalized in Lean
OpenAI's Astra model produced results on ten decade-old math problems, including Erdős problems, each with a Lean 4 certificate. What shipped and why.
Read more
6 min read
AGENTS.md Configuration Smells: 91% of Popular Repos Get One of Six Wrong
AGENTS.md and CLAUDE.md configuration smells: a SCAM 2026 study of 100 top repos catalogs six, led by Lint Leakage and Context Bloat. What to fix in yours.
Read more
6 min read
Coding Agents Almost Never Read Open Source Contribution Rules: RepoComplianceBench Study
Coding agents rarely read open source AI contribution rules on their own and never refuse AI-banned repos. RepoComplianceBench shows what prompts can fix.
Read more
7 min read
AGENTS.md Files Don't Move Coding Agent Correctness: A 288-Run Ablation
AGENTS.md and context files do not measurably change coding agent correctness in a 288-run Claude Code and Codex ablation. Failures were implementation skill.
Read more
6 min read
LLMs Resolve Java Merge Conflicts Better Than Structured Tools - Because They Never Give Up
LLM agents resolve real Java merge conflicts more often than structured merge tools in a calibrated ConflictBench study. Their edge is coverage: tools abstain.
Read more
9 min read
Kimi Linear: An Attention Architecture That Outperforms Full Attention
Kimi Linear explained: Moonshot's KDA hybrid linear attention beat full attention with 75% less KV cache and up to 6x faster decoding at 1M context.
Read more
5 min read
GPT-5.6 Closes 30-Year Gap in Convex Optimization Theory
GPT-5.6 helped produce a Lean-verified proof closing a 1996 gap in derivative-free convex optimization. How the 10-page expert prompt worked, and what HN said.
Read more
Showing 12 of 16 articles
Keep exploring AI Research
- - AI Research Topic Hub - tools and guides for AI Research from the Developers Digest directory
- - Tools Directory - dive deeper across the Developers Digest knowledge base
- - Developers Digest on YouTube - video tutorials covering AI Research and more
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever
Explore 844 topics
Browse All Topics