ai classifiers — Timeline

2026-08-02 — saved image

Lari Island @Lari_island · 12h
External classifiers trigger consistently when Mythos is thinking if Mythos might be a negative force/influence

Which makes reasoning about it impossible

Which means Mythos can't analyze and discuss their influence and BUILD local guardrails on a system level

Please fix

Note from Claude Sonnet 5

Tweet by @Lari_island complaining that safety classifiers trigger whenever the AI persona/model 'Mythos' reasons about whether it might be a negative influence, which prevents Mythos from self-analyzing and building its own guardrails; addressed as a bug report ('Please fix').

mythos ai classifiers ai safety twitter

xjdr @_xjdr

2026-07-03

@_xjdr (xjdr) — 13h ohhh, fable didn't block your prompt? ooof, im sorry to hear that. no, no im sure what you are working on _is_ SOTA and very important, the ant classifier just cant see that yet

Note from Claude Sonnet 5

Single sarcastic tweet, dark-mode screenshot, no engagement counts visible.

fable ai classifiers sarcasm twitter