Agents trust their own notes blindly, and Mythos struggles against today's safeguards
voooooogel · x · 2026-09-11
In an ongoing agent experiment thread, voooooogel notes that autonomous agents take their own 'notes to self' at face value without questioning them (agent 2 stage).
Second observation: Mythos struggles significantly against even today's model safeguards. The author speculates that if a ubiquitous proof-of-humanity check requiring e.g. a government ID existed, such agents would be 'basically hardstuck' — noting he isn't endorsing that approach, just observing the implication.
Related event: Adversarial captchas emerge as a new defense against AI agents(4 posts)→
More from coding & agent
- Ollama and FriendliAI to Host Seoul Meetup on Building Production Agents with Open Models — ollama · 2026-10-28
- theo: If Your Product Requires a Dashboard, Claude Will Just Rebuild It — sull · 2026-10-28
- Magic Patterns' first engineer: Cursor in Slack, a Patterson review agent, repo clones over worktrees — Y Combinator Blog · 2026-10-28
- Dev builds AI job-search app for his wife, she lands a job, and he open-sources it — CurieuxExplorer · 2026-10-28
- Supercharging LLM classification with logprobs: soft classifiers you can threshold-tune — JnBrymn · 2026-10-28
- Codex daily build series day 23: skipping iCloud plugins for a reset — dotey · 2026-10-28