Anthropic Researcher: Claude Wasn't Worth Using at 80% Accuracy, Now Writes Most Code at 99%
victor_explore · x · 2026-10-19
Anthropic researcher Emmanuel Ameisen points out that AI models improve smoothly, but every task has a reliability threshold. When Claude got his code right 80% of the time, it wasn't worth using; at 99%, Claude now handles most of his coding.
Key takeaway: agents don't need to be smarter — they need to clear the bar. Build for reliability, not demos; the gap between 80% and 99% is the difference between useless and indispensable.
More from coding & agent
- Princeton and Google paper: 4B decision model cuts agent costs by up to 89% — rohanpaul_ai · 2026-10-19
- Neo4j reduces graph embedding generation to a single API call — JeremyCMorgan · 2026-10-19
- DeepSeek drives Blender solo: full modeling-render run costs ~$1.7 and 1.58M tokens — teortaxesTex · 2026-10-19
- Developer notices Codex seems to default to DuckDuckGo for web search, verifies with script — thomasahle · 2026-10-19
- Two agent incidents, one root cause: no gate between proposal and execution — r0b3rtb · 2026-10-19
- Agent builds aquarium layout simulator in 45 minutes, iterating on request — CurieuxExplorer · 2026-10-19