• your topics
• add yours

The misery of fitting probabilistic LLMs into rigid SQL schemas

Bits is all you need (and 3.6 bit what you have?) for resource-efficient LLMs?

Which AI Model Is Best at Hacking? A Benchmark of 11 LLMs

Tracker AI – A Veterinary LLM Trained on 300k+ Clinical Cases

Show HN: AI Image Generation Boilerplate (Next.js and Supabase and Stripe)

Training LLMs for Honesty via Confessions [pdf]

We created API-Bench to test how well LLMs execute against APIs

Show HN: Max the Raspberry Pi

Condorcet's Theorem and an LLM Jury: Diminishing returns as group sizes increase

PostHog watches user sessions with multi-modal LLMs (in 5 not-so-easy steps)

Show HN: Lynkr – Claude Code-Compatible Proxy for Databricks/Azure Anthropic

Show HN: Onetone – A full-stack framework with custom C interpreter

The LLM Evaluation Guidebook

Show HN: RAG in 3 Lines of Python

Show HN: KeyboardNotifier: Debug intermittent keyboard/input issues