Cloudflare unveils Clairic, a System One extraction model claiming higher accuracy than LLMs
michellechen · x · 2026-10-20
Cloudflare researchers introduce Clairic, a new "System One"-class extraction model that extracts, computes, estimates and forecasts values from unstructured inputs. It's live in preview on Workers AI as @cf/cloudflare/clairic, with open weights coming soon.
- Inspired by TypeSafe's System One concept (from Kahneman's Thinking, Fast and Slow): fast and precise, contrasting deliberate System Two reasoning of LLMs
- Targets the flood of repetitive structured-output calls to frontier LLMs: invoice totals, delivery delays, repair cost estimates, traffic forecasts
- Claims significantly higher accuracy, lower latency and lower cost than traditional LLMs
More from Models
- Black Forest Labs Launches FLUX 3 Max: 10-Second Videos in 12s, 22x Faster Than Seedance 2.5 — bfl_ai · 2026-10-20
- Smaug Open-Sources SOTA AI Image Detector, Hits 86.7% Recall at 5% False Alarms — bindureddy · 2026-10-20
- Anthropic Email Reveals Claude Mythos 5.1, Opus 5.5, Sonnet 5.5 in Expanded Cyber Verification Program — Sauers_ · 2026-10-20
- Dream-1 launches: 41% of subtasks in 5 minutes, outpacing top LLM agents — gharik · 2026-10-20
- Xiaomi's MiMo-V2.6-Pro is 'the first LLM that thinks like a teenager' — and it's actually good — hrishioa · 2026-10-20
- Cloudflare ships a new 'extraction model': unstructured data in, fields with probabilities out — ritakozlov · 2026-10-20