So cool! Looks like throwing compute and a /goal at RLMs is going to be the ultimate meta…
Btw this is a awesome paper they released about Prime Agent few months back… highly recommend to my RLM bros and sisters.
Show more
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
Show more
I love ultracode for non coding tasks 😼
The people wanted it, here it is.
Full disk search, in milliseconds. 17,000x faster than Finder.
All your ideas are at least worth a prototype.
Because the prototype will be invaluable when you inevitably need to merge that idea into an even better idea.
If you wanna learn how LLMs work you should read this bible of knowledge
"competition is useless, collaboration is everything."
growing a youtube is a durable evergreen skill that can be extremely leveraged for the rest of your career
this is the way!
I've been cookin btw
"when you go from two or three prs a day to 30 plus, because agents make it so much easier to file them, you end up spending all your time reviewing other people's slop" - @theo
full session with theo:
Show more
Already using Grok Bot? Grok Bot 201 is on Friday 9 Oct: teach a Bot by showing it once, let it start on its own, and put several Bots to work together.
I put the entire game of Minecraft inside twitter.. with WORKING multiplayer 💀
elon’s engineer @poteto trusts her bots to ship 2500 PRs a month on a billion dollar company, and you’re afraid to use them on your vibe coded project
I need a "Get out there and Jev, Jev, Jev" shirt.
cool!
I need a hackable Apple Watch Ultra so bad.
