Chatbots and conversational AI
How conversational systems understand, advise, remember, and relate to people.
Start here
Research and essays on time, memory, advice, empathy, and simulated care.
All posts
The Perceived AGI seriesSix papers on one question: what makes an AI feel like someone is there. This page lists them and is updated as each one comes out.
Truth for believable AI: the third Perceived AGI paperPaper three of the Perceived AGI series is on arXiv. It asks whether an AI assistant can be made to say when it is not sure, where a claim comes from, and when it has changed its mind.
Four models checking each otherI stopped asking one model to check my work and started making four of them argue about it. It won a hackathon in August, so I open sourced it.
Entropy in conversational AI: the second Perceived AGI paperPaper two of the Perceived AGI series is on arXiv. When people talk, they hesitate, doubt, and let their mood show. The paper asks how an AI assistant could carry something like that too.
An AI TV channel that takes requestsI spent a Saturday building a YouTube channel that turns live chat messages into AI-generated clips. It cost $31. The code is open source.- LLMs and consciousness research is getting tractionTwo arXiv papers on LLMs and consciousness: the Perceived AGI article and Google's study on language models asserting their own consciousness.
When Claude Code gave up on me- Psychotherapy ads and Anthropic vs OpenAI
What the GPT in ChatGPT stands for
Generative agents and human-like AI behavior
Weekly findings: Meta, crypto and ChatGPT
ChatGPT on non-obvious threats to human existence