Mercury 2.5 LLM hits 770 tokens per second AI Tools AI News LLM & Prompting Q: 8 R: 9 Sep 23, 2026 Summary
LensVLM: Compressing long context as images, expanding only relevant pages AI Tools LLM & Prompting Open Source Q: 8 R: 9 Sep 23, 2026 Summary
LWN Ideas on modernizing the open-source desktop Open Source AI News LLM & Prompting Q: 8 R: 9 Sep 23, 2026 Summary
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text AI Research LLM & Prompting Open Source Q: 8 R: 9 Sep 23, 2026 Summary
Show HN: Jevper – the Jev interface on top of any OpenAI-compatible model LLM & Prompting Open Source API & Integrations Q: 8 R: 9 Sep 23, 2026 Summary
A New Anthropic, OpenAI models make same promise: A little more for a lot less money AI News LLM & Prompting Q: 9 R: 9 Sep 22, 2026 Summary
How to talk about "AI" without adding to the anthropomorphization LLM & Prompting Q: 8 R: 9 Jun 25, 2026 Summary
Show HN: JevBench, a reproducible benchmark for typed decision models LLM & Prompting AI News Open Source Q: 8 R: 9 Sep 22, 2026 Summary
ar SlopShape: Identifying AI-Generated Commercial Web Content AI Tools AI Research LLM & Prompting Q: 8 R: 9 Sep 22, 2026 Summary
Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why AI Tools LLM & Prompting AI News Q: 7 R: 8 Sep 22, 2026 Summary
Writing Rust code that's faster than state-of-the-art libraries by asking agents to make the code faster LLM & Prompting Automation Q: 8 R: 9 Sep 22, 2026 Summary