Skip to content

root / tags / faux-positifs

#faux positifs

3 fiches

Economy & Market Auto-verified translation

Claude Fable 5.1 and Mythos 5.1

Product communication from **Anthropic** published on **September 1, 2026** on anthropic.com (~4,000 words, six sections, 22 testimonials from early-access partners). It announces **Claude Fable 5.1** (general availability) and **Claude Mythos 5.1** (verified access): *the same model, but with different levels of safeguards*.

#Claude Fable 5.1#Claude Mythos 5.1#foundation model

Anthropic — communication produit publiée sur anthropic.com · sans signature individuelle.

AI Coding Agents & Skills Auto-verified translation

Prosecution, Not Code Review

Fourth installment in the ADLC series: Williams reframes code review as adversarial "prosecution" rather than collaborative evaluation. Charter agents to refute ("find what's wrong"), deploy single-lens reviewers with fresh contexts (correctness, security, contract compliance, spec alignment, test quality), act only on verified findings (reproduced by a failing test), and loop until two consecutive passes yield zero findings. Measure calibration by planting known bugs, mutation-testing style. Exit gate: zero open findings, two dry passes, green tests, empty test diff.

#ADLC#prosecution#adversarial review

Chris Williams (@voodootikigod)

AI Coding Agents & Skills Auto-verified translation

Compound Engineering: 3/31/2026

Compound Engineering v2.60, mandatory code review with confidence scoring, hardened plan→work→review pipeline

#Compound Engineering#mandatory code review#confidence scoring

Trevin Chow