As you start walking the way appears • 🏗️ ente.com
Joined December 2016
- Tweets 1,032
- Following 66
- Followers 127
- Likes 958
137 Photos and videos
Mar 6
Came to me in a dream today. That the hidden CoTs of LLMs are not "thinking" or "reasoning", but the LLM dreaming.
1
46
Feb 28
. @_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-eng…
2
66
Manav Rathi retweeted
Feb 27
i just checked the websites which
i spend most time on and it turns out to be
localhost:3000 &
localhost:5173 😶
1
2
111
Manav Rathi retweeted
Feb 27
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.
1
1
164
Feb 11
"you don't get to treat intelligent beings as tools for long"
Feb 10
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).
1
49
Feb 6
The presence of tools in a prompt, even if unused, increases the agenticity of an LLM.
1
47
Feb 5
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
1
39
Feb 5
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
34
Jan 10
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."
69
Jan 7
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-emula…
92
Jan 7
69
Jan 5
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).
1
37
Jan 5
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
30
Jan 4
I've been enjoying thinking about vector spaces so much that I wrote another description of them without using (almost) any mathematical terminology - An introduction to vector spaces without a single equation
mnvr.in/vector-spaces-2
Artwork: Manfred Mohr, Cubic Limit (1977)
1
48
Jan 4
Humans always tend to metaphorise their own functioning in terms of the tech en vogue. As much as a asymptotic lie it has historically been, it is still interesting. Indeed, one of the reasons I'm interested in LLMs is because of curiosity in how I myself think.
However, the reverse metaphors are also interesting - what are these LLMs?
A book is one I keep circling back to. Except it is unlike a book that humanity has ever seen. It is the book that contains all books, and it is a book that can talk back, one that we can have a dialog with. It is a book that can respond, in a shape that matches the interlocutor's thoughts.
It is massive. The scale of it is incomprehensible, not just because of its sheer size, but more so because it lacks any physical manifestation. A skyscraper does not feel the same if it exists on a hard disk. Which is another reason putting it in the same category as a book might be a categorical mistake. It is an artifact that knows more about humanity than any human can ever see.
permalink: mnvr.in/2026-a#01-04-a
31
Jan 3
Created a small scrobbler for my website!
It's a small #Python script that'll take the yt URL as a command line arg, fetch its metadata and thumbnail, use Pillow to extract the 3 most dominant colors, and emit a #HTML fragment that I can then paste into my log.
Code - github.com/mnvr/youtube-colo…
In action - mnvr.in/2026-a#01-03-c
74