I had such a great time at @aiDotEngineer Europe last week !
Except for one thing: My workshop went terribly because I vibe-slopped a little bit too hard half an hour before it started and was too frazzled to recover
So I promised everyone I'd make a video recording of what it was meant to be.
Here's that video! This video is relatively long and aimed at the workshop audience. But if there's any interest, I'll make a 3 minute version
In short, I believe that (maybe)
1. Agent harnesses should be modelled as stream processors that call append({ event}) and stream() an append only event log
2. All state in agent harnesses should be event-sourced
3. Harness plugins are just stream processors, too, and can run on other machines from the "harness" itself
4. All agents should have a public URL that events can be posted to
5. You should be able to append the source code of a stream processor to a stream and then it magically runs on that stream
To prove it, we make a "coding agent" built on @tan_stack AI and @cramforce 's just-bash and deploy it to a real stream at https://t.co/GE8jOPy7pX
And because @badlogicgames told us to use our brain more, I though I'd try to actually write the code by hand
You can try this yourself by using this repo here https://t.co/bk2ikSbSrt
@EthanLipnik are you familiar with Unison?
worked on this a few years back and honestly ended up borrowing / extending most of the concepts from Unison but implemented in language-agnostic way
A preview for Pro users: a new personal finance experience in ChatGPT.
Pro users in the U.S. can securely connect financial accounts, see where their money is going, and ask questions based on the information they choose to connect.
Your full financial picture, now in ChatGPT.
very passionate about this and know how hard this is, @essamsleiman is doing some really cool work here and very excited to see where he goes from here
We’re launching @JudgmentLabs today and announcing $32M in funding.
As AI agents take on more of the work that creates economic value, they generate massive amounts of production data: the clearest record of how they behave with users, software, and the real world.
Judgment builds infrastructure for improving AI agents from production data.
@RhysSullivan this has been really bad lately
my guess is something got messed up with trying to encourage async use of subagents and instead of correctly waiting it does this instead :/