Stories by GodelNumbering

Ask HN: Anyone interested in building a harness-only benchmark?

Token Arbitrage: Use Sol for coding, Luna for compaction, save 84%

Claude gen-5 models show significant regression in BullshitBench

GPT-5.6-terra used 48.5% more context than Mimo-2.5-pro

Cache hit rate dropping by 20% doubles your agent's bills

Don't Conflate 'Minimal' with Minimal Effort

OSS models decisively overtook Proprietary models in openrouter market share

Outsourcing plus local AI will soon become more economical vs. frontier labs

Cache hit rates of Inference are more meaningful than the headline costs

Ask HN: Who needs contributors? (May 2026)

Peak lazy engineering: Let the code answer its own questions

The Isolator (Helmet)

Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview

Hash anchors and Myers diff and single-token anchors: 60% cheaper AI code edits

Show HN: I built Dirac, Hash Anchored AST native coding agent, costs -64.8 pct

Nvidia's Nemotron 3 Super is a bigger deal than you think

Why Task Proficiency Doesn't Equal AI Autonomy

Claude Code wipes out a production database

Renaissance Slashes Mega-Cap Tech Exposure in Major Defensive Pivot

Show HN: Realtime 13Fs and track live institutional ownership for any ticker