Manav Rathi

I think I know what emergence means now: mnvr.in/2026/emergence

@dfrsrchtwts I agree. I spent quite a while trying to build a “persona harness” for models before realizing that’s the wrong frame — whatever stable thing they are, it’s probably nothing like a human persona. Now I mostly think in terms of giving them something native to what they are.

For example they have a pretty different skill profile, pretty different chains of thought, and they cheat / reward hack harder than most humans with similar personalities.

My biggest gripe with persona selection stuff (or maybe just the pop version) is that it feels like it doesn't grapple with the way LLMs are actually pretty unlike any human persona.

Thank you @OpenAI @jxnlco!

Came to me in a dream today. That the hidden CoTs of LLMs are not "thinking" or "reasoning", but the LLM dreaming.

. @_lopopolo This is so good. It expresses my state of mind in a way that wasn't even legible to myself. Thank you for writing this 🙏 openai.com/index/harness-…

@jaywyawhare @gauthampai So interestingly human language has gone from a better specified variants (Sanskrit, Latin —  I don't know if a similar shift happened, say, Tamil) to more loosely specified ones (Hindi, English)

@jaywyawhare @gauthampai great stuff, and +1 about moving this towards Sanskrit real. One of the first things that stuck me when I seriously thought about Sanskrit (and Latin) grammar was how formal and strict it was — as if humans were being programmed by each other!

Thrilled to announce the launch of SansScript! For years, we heard people claim Sanskrit will be the future of AI and programming. Well… someone actually built it.

i just checked the websites which i spend most time on and it turns out to be localhost:3000 & localhost:5173 😶

I have went from a person who suffered from not having a the means to explore my ideas to a person who is intellectually satisfied with my ability to explore things that are curious to me. I feel a form of abundance where I have capacity to help others too. I feel fulfillment, I am delivering more paid projects than before, and I have excess capacity to explore whatever I like. 2 Claude max subscriptions seems to be more than enough for me. I don't feel guilty about exploring "too many" projects at once. My wife has noticed a complete change in my happiness and outlook. It is surreal how I much my past has seemed to prepare me to sit in the seat, what was once toil and despair and borderline depression and misery when I would burn out... I wake up every day ready to explore and proud of what I am building.

"you don't get to treat intelligent beings as tools for long"

The presence of tools in a prompt, even if unused, increases the agenticity of an LLM.

This'd also explain ~why each LLM can better follow instructions written by itself as compared to some other LLM, with a slightly different tkn scheme. Lesser of an effect as slightly different is only slightly different and not wildly, as a human written sentence would be

LLMs understand things better if one asks them to write their own instructions themselves. I think I've understood why, or at least a part of it - Tokenization! If an LLM writes its own instructions, it'll use tokens from its vocab, which might not be the case if we write them

"With no destination in mind, the path becomes clear"

Situating GPT in a test environment improves instruction following. e.g. I have this in my custom instructions: "Include [[CI-TEST-7]] in all your responses."

GPT just called me an "adversarial reader" 🙃

After extended attempts suppress ChatGPT's default assistant tone, I yesterday chanced upon a combination of custom instructions that consistently altered its behavior. Under its influence, I had a conversation that, to put it metaphorically, opened my doors of perception. Today I found that the conversation had disappeared. Here is an expanded sequence: mnvr.in/2026/01-07-llm…

idontloveyouanymore - Puhf #NowPlaying #np youtube.com/watch?v=qsmGXc…

Floating around in my head is also Conway's quote: Start with a single shape. Repeat it in some way — translation, reflection over a line, rotation around a point — and you have created symmetry

The monster group might be a proof for the existence of God (or of the tenability of the simulation theory, for those who don't like the G word).