# "llm assistant personas seem increasingly incoherent (some subjective observations)" by nostalgebraist

Page: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/llm-assistant-personas-seem-increasingly-incoherent-some-subjective-observations-by-nostalgebraist
Text version: https://stenobird.com/podcast/lesswrong-curated-popular-5643401/llm-assistant-personas-seem-increasingly-incoherent-some-subjective-observations-by-nostalgebraist.md
Podcast: [LessWrong (Curated & Popular)](https://stenobird.com/podcast/lesswrong-curated-popular-5643401)
Published: 2026-04-29T19:45:16+00:00
Episode link: https://www.buzzsprout.com/2037297/episodes/19099089-llm-assistant-personas-seem-increasingly-incoherent-some-subjective-observations-by-nostalgebraist.mp3
Audio file: https://www.buzzsprout.com/2037297/episodes/19099089-llm-assistant-personas-seem-increasingly-incoherent-some-subjective-observations-by-nostalgebraist.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/llm-assistant-personas-seem-increasingly-incoherent-some-subjective-observations-by-nostalgebraist
Duration seconds: 946

## Resource

(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...

## Actions

- request_transcript: `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.
- read_markdown: `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.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.