news, tips, and reviews that make thinking machines useful
X
Tag archive
Everything we’ve published under AI Safety so far.
Follow this lane
AI Safety appears in trust, safety, and evaluation, a useful buying-intent lane for relevant AI products and services.
Fastino’s 300M-parameter GLiGuard reframes moderation as classification instead of generation. If the benchmarks hold up, the lesson is simple: safety rails should be cheap enough to run everywhere, not another heavyweight model call.
Petri 3.0 turns Anthropic’s open alignment-testing tool into a more hackable, more realistic eval stack under Meridian Labs. Useful, if buyers treat it as a test harness instead of a trust sticker.
Anthropic says Claude Mythos Preview can find and exploit serious software flaws at a new scale. Project Glasswing is its attempt to put that capability in defenders’ hands before attackers get the same advantage.