Episode
"llm assistant personas seem increasingly incoherent (some subjective observations)" by nostalgebraist
- Published
- Apr 29, 2026
- Duration seconds
- 946
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/llm-assistant-personas-seem-increasingly-incoherent-some-subjective-observations-by-nostalgebraist/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/llm-assistant-personas-seem-increasingly-incoherent-some-subjective-observations-by-nostalgebraist.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
(This was originally going to be a "quick take" but then it got a bit long. Just FYI.) There's this weird trend I perceive with the personas of LLM assistants over time. It feels like they're getting less "coherent" in a certain sense, even as the models get more capable. When I read samples from older chat-tuned models, it's striking how "mode-collapsed" they feel relative to recent models like Claude Opus 4.6 or GPT-5.4.[1] This is most straightforwardly obvious when it comes to text...