Pinned Tweet
When I was a kid, my uncle called me 1-Adam-12. It’s from an old show he loved to watch before my time that I’ve never seen.
It stuck with me because he was so much fun to be around and enthusiastic about it.
He passed away when I was 15, nearly 30 years ago.
I chose @ZeroAdamEleven as my handle when I was learning to code. Programmers will understand.
I think of him often.
1
78
This is a great talk
How do always-on, proactive agents like @Bot work?
Watch my lecture at Stanford CS146S:
2:35 How we got here
6:13 What changed in the models
10:06 Inside an always-on agent
18:07 The harness
27:26 Context engineering
34:26 Where this is going
19
Adam retweeted
there’s something quite awkward about all the personal agents in the current hype cycle
muse, grok bot, instinct, dots, and whatever google, anthropic will come up with
none of them is “mine”
i’d be trusting a vendor for some of the most sensitive data about me and bet on them handling it with extreme responsibility. what if they have a data leakage incident? what if they hired a wrong employee? what if they simply break bad?
i’d also be betting on their model. right now i’ve set up a lot of my stuff in grok bot, but what if their model falls behind? what if another model becomes 10x better on pure intelligence? then i’ll either miss out on a better assistant, or have to bite the bullet and do a full migration
i’d also have to bet on their product. they may not build the features i want. they may not allow me to customize enough. and one day my assistant may show me ads
that feels like way too much betting than what i’d be comfortable with, if i truly want literally everything in my life to go through and be taken care of by an assistant
with all that considered, i’m more bullish on open source personal agents that run on people’s own computers. but i think these open source projects have to break out of the assumption that their users are developers and they can just throw a repo at them and ask them to launch a terminal
a well polished, fool proof, community maintained, vendor agnostic, free personal agent that everyone can run by themselves without locking into a SaaS - that’s what i think many people will need
This clip is going viral, and I too agree with it.
Props the engineer that told AI to solve this edge case. Very nice touch 👏👏👏
23
This turned out to be a major fail. It constantly got stuck and burned way to many tokens for what it did. Grok build is not good for doing a block of work in large application. It's better suited for starting from scratch to make toy apps.
Trying my first long run with @grok build.
Impressions:
I love that it works in the cold and I can check on it in the Grok app on my phone.
It takes way longer than having Grok bot handle individual cloud sessions in Cursor in a planned sequence.
I don’t like that I can’t see what the subagents are doing. I have no idea if they are stalled on something. When I ask for a status update it’s like, oh yeah, I was sitting there twiddling my thumbs for nothing.
It will get better from here, but I kinda think Cursor + @bot would have knocked out 10 of 10 tickets before I woke up. Only 3 are done in this run.
40
Trying my first long run with @grok build.
Impressions:
I love that it works in the cold and I can check on it in the Grok app on my phone.
It takes way longer than having Grok bot handle individual cloud sessions in Cursor in a planned sequence.
I don’t like that I can’t see what the subagents are doing. I have no idea if they are stalled on something. When I ask for a status update it’s like, oh yeah, I was sitting there twiddling my thumbs for nothing.
It will get better from here, but I kinda think Cursor + @bot would have knocked out 10 of 10 tickets before I woke up. Only 3 are done in this run.
I’ve come around on this. It took a bit, but now I never write code manually.
i've been programming for roughly two decades now
idk how programmers are not hyped about all the agentic coding, orchestration, skill development, and self-improving systems
what's the alternative, write <Dialog> manually again?
45
If you’re paying for an AI dictation app you’re wasting money and potentially giving away everthing you say to a third party.
I found handy.computer/ and it works great and nothing leaves my machine and it’s free.
89
Yikes 😳
BREAKING: OpenAI might have stolen another major proof.
In a detailed Mastodon post, which I report in full in the comments, Andreas Thom presents several pieces of evidence suggesting that OpenAI may have trained Astra on conversations in which he and Gábor Kun were working on Gromov’s soficity conjecture, one of the ten problems OpenAI later announced Astra had solved.
I know Andreas. We met several times early in our careers. He is an exceptional mathematician, a leading expert on sofic and hyperlinear groups, and one of the most respected scholars in the field. He has spent two decades working on this problem.
If his account is correct, this is not a minor dispute over attribution. It would mean that unpublished human work was absorbed into a model and then presented to the world as a breakthrough by the model itself.
And if the allegations raised by Levent Alpöge, Tristan Buckmaster, and now Andreas Thom are all substantiated, we are no longer looking at isolated incidents.
We may be looking at one of the greatest intellectual scandals in the history of science.
AI is not discovering new mathematics.
AI is stealing human discovery.
35

















