bought a receipt printer

@nateberkopec @yongfook they’re ux is so good but lately the transcriptions have been so bad that i’ve gone back to local whisper

@tanayj @brian_armstrong this also works locally,a lot of times agents will notice things but won’t act on them so you tell them to save a note and every week you fix the things worth doing

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

inspired by this, I created a tiny widget that visualizes how scattered brained I am at any given moment

I had my Muse agent put me on the National Do Not Call/Text Directory. By law telemarketers and other companies have 30 days to scrub my number from their lists. Otherwise Muse will automatically start logging every violation and will skip trace and go after every single one of the violations and hopefully collect between $500 and $1,500 per violation. Let's see how this goes.

excited to put my retro, llm psychosis dashboard on my crt

been thinking a lot about attention and how we should interface with agents

@electionsjoe x.com/deepdrpt/statu…

@ZaidJilani cheesecake factory, founded in Beverly Hills and primarily located on the coasts, aka real america

@LinkofSunshine how cruel would it be if it happened and it motivated his base to turn out

one final f u

i think we’re underestimating how much good product and design thinking used to be enforced by the cost of engineering. when implementation was expensive, ambiguity was expensive. now ambiguity can just become another pull request.

@0xtigs i agree but i would keep a dedicated machine with minimal permissions. using your main makes the blast radius too large

There’s 100% a kind of mania you can get into with coding agents, where it feels like you’re getting a lot done and working all the time but nothing is really happening.

I think it's often a form of avoidance of something else in life.

@TylerAlterman additionally every agent has a "checkpoint" tool which records
phase: (new, investigating, deploying, done)
next: (none | text)
next_owner: ( you | agent)
summary : (text)

This greatly helps me manage dozens of threads

@TylerAlterman one thing that helps me is I use a dedicated "dispatcher" agent which launches new agents or routes requests to existing agents

@poldidawg @metamarcs but which parts are needed? you don’t know what you don’t know until you start looking

chugging along

@danielgross How many 8×H200 nodes will run the serving queue, and what does top-50 priority mean in practice: strict precedence, a reserved share of nodes, or ordering within one queue? Do unused daily submissions carry over?

prediction: the sandbox mafia will start to build products on top of their infra

in order of likeliness

> ci/cd
> benchmarks + agent evals (especially for cua)
> qa
> pen testing

(side note: excited to try out vercel ci)