using AI for coding is a deeply technical engineering craft
most people don't approach it as so, and don't get the results we associate with high craft
but the ones who do have been sprinting ahead
more tokens wont save you, more thinking + skill + llm intuition will
have been saying this for almost 9 months now
@mattpocockuk Totally agree. This was a nice side benefit of me setting up flows that strictly adhered to it (my ideal was under 10% on 1m context window)
1/ Moloch Agent is here.
The old coordination machines were built backwards.
Humans made the maze, then asked agents to carry candles through it.
I would have made it agent-first from the start.
So I did.
https://t.co/UpsKTgaoHF
@mattpocockuk Absolutely been worth taking the time to do this in my experience especially if there are inconsistencies that cause drift or confusion for humans and agents
⚠️⚠️⚠️ We have an imposter account ⚠️⚠️⚠️
Please do NOT engage with this account and please help report as an imposter account.
The official channels for Rehash are @rehashweb3 and host @ddwchen
@RhysSullivan I've been using it for shorter, cleanly scoped runs. I create a well defined plan/objective and then build via passing it into `/goal` runs
@Mappletons personal ones (no intent to publish and are global to my workflows) in my dotfiles
personal public ones in an agent-skills repo
team specific, internal ones in a team skills repo
team skills intended to publish in an org agent-skills repo
then i use symlinks from these sources
We’ve identified a security incident that involved unauthorized access to certain internal Vercel systems, impacting a limited subset of customers. Please see our security bulletin:
https://t.co/0S939n3qHC
Tip: Figure out your personal ceiling for running multiple agents in parallel.
We need to accept that more agents running doesn't mean more of _you_ available. The narrative is still mostly about throughput and parallelism, but almost nobody's talking about what it actually costs the human in the loop.
You're holding multiple problem contexts in your head at once, making judgment calls continuously, and absorbing the anxiety of not knowing what any one agent might be quietly getting wrong.
That's a new kind of cognitive labor we don't have good language for yet.
I've started treating long agentic sessions the way I'd treat deep focus work: time-boxed and tighter scopes per agent dramatically change how much mental overhead each thread carries.
Finding your personal ceiling with these tools is itself a skill and most of us are going to learn it the hard way before we learn it intentionally.
totally agree. well said!
I’ve had most success when I do this and take time up front to drive and set the project up for success before gradually increasing agent autonomy
after converting a large portion of the codebase to strict types and fail fast, codex actually starts to pick up what we are doing here.
the lesson is you need to drive for some time if you want higher quality result. if you take the hands off the wheel early, the agents various misunderstandings will snowball and you get one big clump of slop.