Building https://xitter.cf/t.co/1bZdsKayV9. Toolmaker, motorcyclist, father, hunter, American, husband to @jeeyunit
San Jose, California
Joined July 2006
- Tweets5.5K
- Following1.2K
- Followers1.7K
- Likes21.8K
Using browser-use to self-verify agent-desktop timeline cards work
browser_exec and the new desktop_exec tool show live frames and screenshot evidence in the Paseo timeline
Reid Burke retweeted
Agentic coding benefits from powerful abstractions, just like humans do.
AI may well be able to write massive software projects “from scratch”, but that almost certainly isn’t the fastest / highest performance / highest security / most token efficient way to do things. Good building blocks matter.
In addition to RL’ing the agents on final task loss, we should try to get them to regularize the building blocks as well. What would the standard library look like that makes the agents most effective?
It is likely at the limit that it turns out to be some alien organization of code, but given the existing human-bias in training, I bet that in the near term it would be lovely code that old programmers would appreciate.
I suspect the same could be said for mathematics, but that is out of my lane.
Driving my Mac with agent-desktop in @paseo_sh
Reid Burke retweeted
we will need to rebuild and rewrite much of software to adapt to a new, faster pace.
code used to arrive one drop at a time. soon, if not already, code will be written as if it were a continuous stream, like a violent river twisting and turning as it pleases.
this is not a new thing: big tech cos have had to deal with this with the enormous scale of their engineering teams. but now ai has brought an incredibly elastic and capable workforce wielded by every engineer. this is your problem now, and the only way to adapt is to evolve your systems so agents - even and especially the ones with little context about the right way of doing things - can thrive. make the easy thing the right thing.
your codebase is becoming organic architecture. agent contributions grow around the constraints and guardrails you’ve designed. good software engineering matters even more now! and no, the continuous stream of code is not something you have to watch helplessly. be more ambitious and design systems, frameworks, and languages to control the chaos.
the time for mourning coding is long over
Personal supercomputers are awesome
January’s SOTA intelligence for coding in your home for $4k and 65 W of power is wild
Keynote Interchange Format (.keyx) is an open JSON-based bundle file format designed to be readable and accessible to external tools, developer workflows, and AI agents — out today!
Huge day for Creator Studio today.
Our new in-app assistants can help you get things done in record time. MCP allows you to bring your own agent if you want. And an open source format for Keynote (and Python library!) so you can create Keynote documents programmatically on any platform.
Super proud of the team. Hope you love it!
I’ve found success doing this with screenshots, HAR files, and React Performance Track recordings with specific claims against them.
Agents present the claims against the evidence together in @paseo_sh timeline cards and the worktree’s evidence directory.
Good combo with @poteto’s pstack create and maintain verification skills.
Want better quality output from your agent? Give it a way to verify its own work.
Love what Warp is doing here: every agent gets a computer and brings back a video of what it did. I do something similar in my workflow - on top of E2E tests, Claude gives me recorded videos + screenshots as part of the evidence work is "done".
My bet is verification becomes one of the most important problems to work on this year.
I do not use statecharts enough but that’s about to change
Before the agentic age I used XState at Yahoo Mail to make web push delivery a lot more reliable, but I was working full time on it for a few months
Going to be very nice to use this for improving all kinds of work
i've been a bit quiet - working on a new companion skill that will help your agents draw these beautiful statecharts/diagrams + check them against the specs you made with /create-formal-verification-skill in pstack!
it now uses Pele from @kepano too which is why they look so good.
will release soon!
