Astra still generates fake unrelated criticisms when fact-checking, user finds
AndyMasley · x · 2026-09-07
Andy Masley had Astra fact-check something he wrote and found it still does what all LLMs do: come up with fake unrelated criticisms — e.g., disputing "data centers didn't add water pollution here" by arguing water pollution "can definitely still be a problem in general." Even frontier models struggle to respect the boundary of a specific claim in fact-checking tasks.
More from Models
- OpenAI's Astra impresses with 3D interactions: directional sticker peeling demo — arena · 2026-09-08
- sanoTTS: a 337KB neural TTS that runs on a $3 ESP32-S3 or in your browser — alexcovo_eth · 2026-09-08
- Astra saturates Epoch AI's EBR-bench with 100% score in two playthroughs, beating top human — Jsevillamol · 2026-09-08
- Grok 4.7 reportedly being stealth-tested in Grok Bot ahead of release — mark_k · 2026-09-08
- Chess benchmarks questioned: a model could just download Stockfish and crush Magnus — iruletheworldmo · 2026-09-08
- Claude Fable 5.1 system prompt reveals why Claude 5 models wrote so badly — dbreunig · 2026-09-08