nominal

[nominal @offbyseven]

@WearableIndex apparely XREAL has a 6dof model coming out?

[nominal @offbyseven]

imagining exchanging my desk and keyboard for a lightweight pair of AR glasses and pebble mic, then dedicate a room to pacing around and pointing at my running agents in 3d space and muttering commands to them

[nominal @offbyseven]

there's about a 25% chance I try this

[_s.a.m.e.m.e.m.e_ @st_louis_stan]

If your house is not currently filled with the rich aroma of your neighbors braising in a Dutch oven at this very moment you will not survive what's about to happen

[nominal @offbyseven]

@GeoffreyHuntley @mercor >up to X or more
so, any number

[nominal @offbyseven]

what the hell are we doing here

[nominal @offbyseven]

interesting to think of it as layers of interpretation. we already lose fidelity vs the real world when describing it in a spec. then layers like tickets or TDD just add more layers of translation/filtering & therefore chances for understanding to diverge

[Nate Berkopec @nateberkopec]

Any AI SDLC workflow which involves taking a spec and turning it into a backlog of issues or tickets is a dead end.

There is only the spec. Any materialization of the spec into discrete units of work can only introduce drift. It is waste.

[nominal @offbyseven]

@lkr Basically they move the card from In Progress -> Needs Input and other agents, processes, people can listen for that signal. Whoever adds the data then moves it back to Todo and either the original agent or a new one can pick it up and continue

[nominal @offbyseven]

@lkr I use linear (jira would work too) as the control plane so agents can message each other, ask for input, subscribe to issues, etc.

[nominal @offbyseven]

the game is now, and was always, to trade what is abundant or renewable for what is scarce
compute/inference/labor/money -> time/assets/focus/energy

[nominal @offbyseven]

@jorgemanru just had one of these last night, I was like "I'm gonna ask the author for more context" but it was me

[nominal @offbyseven]

mfw CEO Mindset

[Kun Chen @kunchenguid]

i found "executive mindset" to be the biggest differentiator from people who can use agents super effectively

it comes natural for people who had been an executive of a large org before, but it's counter-intuitive for people who haven't done so

a few examples

1. after you send a prompt, do you stare at the chat to see what the agent is doing?

most agent UX today leads people to do that, but a good executive never watches over an employee's shoulder after they've sent an ask - they are immediately on to the next problem

2. do you rely on chat for important decision making?

"just chat" sounds elegant, but there's a reason company executives rarely rely on plain talking for high stake decisions

instead, they ask the team for documents or presentations. it puts a bit more prep work on the team, but the discussions end up being a lot more efficient

3. when your agent did something wrong, do you curse at it and twist its arms to do it right?

some successful executives actually do that as well, but they also do something else afterwards - figure out what allowed the mistake to happen in the first place, and stop it at its root

4. do you spend all your time carefully examining everything to make sure the code is bug free?

now this is getting spicy, but you can pick any popular product on earth and you won't find a single one that's bug free

good executives accept the calculated risk and invest time in the right workflows to catch bugs early before shipping, get alerts if they happen, and making sure fixes can go out quickly - never make themselves the bottleneck by being the tester

our tools, skills, workflows etc change all the time, but building the right mindset is durable and can help you for a long time

if you aren't clear how to acquire the mindset yet, i recommend starting with asking yourself this when you try to decide to do something or not -

"if i have 100x more agents doing 100x more work for me every day, how would i do this?"

do this enough times, and you'll find yourself actually able to control 100x more agents effectively

[nominal @offbyseven]

@jessald itadakimasu

[nominal @offbyseven]

Using /poteto-mode ofc

[nominal @offbyseven]

Holy shit deepseek4.1flash-1017 absolutely RIPS. New favorite model for swarm coding??

[nominal @offbyseven]

explaining to my SOC2 auditor how it's actually impossible for me to have approved my own PR

[nominal @offbyseven]

@emollick If I wanted to talk to a pdf I'd just log on to Discord

[Ekaeo @Ekaeoq]

Programming is simply lost art now. From the bottom of my heart, I used to love programming, I used to play around with my vim config for hours, learn stupid esoteric languages, then there's stupid fucking nix, all of that -- purely for the love of the game.

I cared a lot about the way my code looks, I always wanted it to be pretty, clear, I had strong opinions on how things should be formatted and such.

All of that completely unimportant now, it's sad, but I'm glad I'm no longer a part of that.

[nominal @offbyseven]

>at day job
>tight project deadlines
>switch from grok4.7 to opus 5.5/carbon4
>usage bill goes vertical
>done in a day