Manav Rathi

As you start walking the way appears • 🏗️

[Manav Rathi @mnvrth]

@shawn_pana @nischalsharma_ I had a similar concern, so made a variant mostly for myself - https://t.co/f0YSGSull9

All that said though, @shawn_pana thank you for smux!

[Manav Rathi @mnvrth]

I think I know what emergence means now:
https://t.co/w7ArL1hI9c

[Manav Rathi @mnvrth]

@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.

[Manav Rathi @mnvrth]

Thank you @OpenAI @jxnlco!

[Manav Rathi @mnvrth]

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

[Manav Rathi @mnvrth]

. @_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 🙏

https://t.co/mtnT2vCohT

[Manav Rathi @mnvrth]

@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)

[Manav Rathi @mnvrth]

@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!

[Aswin Asok @_aswin_asok_]

i just checked the websites which
i spend most time on and it turns out to be

localhost:3000 &
localhost:5173 😶

[dad chords @dadchords]

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.

[Manav Rathi @mnvrth]

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

[j⧉nus @repligate]

If I could have everyone developing or making contact with AGI & all alignment researchers read one book, I think I might choose Mistress Masham's Repose (1946).

[Manav Rathi @mnvrth]

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

[Manav Rathi @mnvrth]

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

[Manav Rathi @mnvrth]

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

[Manav Rathi @mnvrth]

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

[Manav Rathi @mnvrth]

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."

[Manav Rathi @mnvrth]

GPT just called me an "adversarial reader" 🙃

[Manav Rathi @mnvrth]

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:
https://t.co/ZxTC5RRVab

[Manav Rathi @mnvrth]

idontloveyouanymore - Puhf

#NowPlaying #np

https://t.co/DVV7of7X1N

[Manav Rathi @mnvrth]

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

[Manav Rathi @mnvrth]

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).