Topic

llm-evaluation

4 issues covering this topic

Node.js patches six permission bypasses; Zeta2 improves accuracy

Mistral Vibe 2.0 subagents, sub-200ms transcription, Claude 5

Biome v1 ships with formatter options, Go 1.26 modernizes

Claude Opus 4.8: 4x fewer agent errors, same cost

Get llm-evaluation updates in your inbox

Dev Signal covers AI tools, benchmarks, and developer workflows — free, every weekday.