Autoregressive Language Model on the 6502 Processor AI Research Hardware AI Tools Q: 8 R: 9 Jul 31, 2026 Summary
X An internal OpenAI Astra model solved 10 major open math and CS problems AI News AI Research LLM & Prompting Q: 7 R: 9 Aug 2, 2026 Summary
Persistent State Machines: LLM Attention with INT4 In-Memory Cells AI Research Hardware Q: 9 R: 9 Aug 2, 2026 Summary
X Assessment of open AI math results AI News AI Research LLM & Prompting Q: 8 R: 9 Aug 1, 2026 Summary
We need more than a metaphor: here are testable diagnostics for comprehension debt AI Tools AI Research AI News Q: 8 R: 9 Aug 1, 2026 Summary
Predictive Speculative KV Replication for Bursty LLM Inference AI Research LLM & Prompting Q: 8 R: 9 Jul 31, 2026 Summary
ar ORCA-bench: How Ready Are Language Model Agents for Oncall? AI Research Monitoring DevOps Q: 8 R: 9 Jul 31, 2026 Summary
Is AI Reasoning Right for the Wrong Reasons? AI News LLM & Prompting AI Research Q: 9 R: 9 Jul 31, 2026 Summary
A Google reveals Gemini Robotics 2.0, promising improved dexterity and safety AI News AI Research Q: 9 R: 9 Jul 30, 2026 Summary
I flagged two research papers for fake authors and both were accepted as orals AI News LLM & Prompting AI Research Q: 8 R: 9 Jul 30, 2026 Summary
Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it AI News AI Research Open Source Q: 8 R: 9 Jul 30, 2026 Summary
You can't solve computer use by ignoring the interface Automation AI Research AI Tools Q: 8 R: 7 Jul 30, 2026 Summary
Show HN: I audited my AI leaderboard scale – every score dropped 6-15 points AI News AI Research Q: 8 R: 9 Jul 30, 2026 Summary
T Kuna: Decompiler Development in the Age of Coding Agents AI Tools AI Research Open Source Q: 7 R: 8 Jul 29, 2026 Summary
AI system 'Theo Conjecture' solves 35-year-old math conjecture, finds a term no one predicted AI Tools AI News AI Research Q: 8 R: 7 Jul 29, 2026 Summary
A What happens when you put AI to work deciphering lost languages? AI Tools AI Research LLM & Prompting Q: 9 R: 9 Jul 29, 2026 Summary
ar HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following LLM & Prompting AI Research Open Source Q: 8 R: 9 Jul 29, 2026 Summary