Tweet épinglé
Patrick Lu
1.7K posts
Patrick Lu
@lightninglu10
Building agents that automate everything in your company: https://t.co/hhaxPjaLDL / ycombinator fellowship / top 80 NA FIFA player
Berkeley, CA Inscrit le Ekim 2012
202 Abonnements325 Abonnés
@tengyanAI I’ve found that working with agents I can work a good 12-14 hours before I’m tapped out each day. This is up from ~8 before.
Agents let me do more work through sheer volume, as well as sheer time.
Completely changed the way I work
English
something i've noticed: AI agents create a weird new kind of burnout. esp for young people.
a lot of ambitious 22 year olds are going to think the answer is simple:
- spin up more agents
- ship more code
- sleep less
- outwork everyone
and for a while, it will feel incredible.
you can keep multiple agents running, feed them tasks, review outputs, fix mistakes, make decisions, and keep the whole loop moving.
the problem is that the work no longer drains you through typing. it drains you through judgment.
More attention.
More context switching.
More verification.
More decisions per hour.
so instead of 8-10 normal productive hours, you might get 4-5 extremely intense hours before your brain is fully cooked. and you feel numb until you sleep properly and reset
some of my friends are already burnt out. they don't say it out loud but i can tell.
the agent can keep working 24/7.
the human still has a hard limit
English
@potetm That means you’re doing it wrong. Let the LLM’s make most of the decisions. They’re smarter than you.
English
the real reason you feel so exhausted after coding with LLMs.
Andrew Rose@__drewface
Decisions are harder than tasks.
English
Patrick Lu retweeté
The B+ employee pandemic is real.
Always "on it." Calendar blocked. Slack green. Never misses a deadline.
Company still not moving.
Bc they're all professional seat warmers.
No edge. No urgency. Never fixing any gaps.
They won't push back on anything.
Just smile, execute, cash checks.
Founders love them because they're "low maintenance."
But what they actually are is low impact.
U can have an entire team of B+ employees and wake up a year later in the exact same spot.
Congrats, you’ve officially normalized mediocrity.
English
Patrick Lu@lightninglu10
English
Each is working on a different feature. Manage them by kicking them off and checking in periodically. Each of them after a certain point need no hand holding. UX of my app shows me when it needs my attention.
Each agent goes thru gets reviewed by another agent in GitHub, gets the review back into its own context, then verifies its own work by spinning up its own servers and QAing like a human would. Works incredibly well.
Linked is my commit chart. This isn’t vaporware, it’s real software being shipped to real customers.
Hth
English
@a16zwagie @DissidentClint Lmao. Why didn’t I just use my hands to fold them then? 😂
English
This is incredible. $2500 to never fold laundry again! WUT
Many people are creeped out by humanoid robots. The aesthetics of this are a game changer.
Aaron Tan@aaronistan
We are hosting the largest showing of Lume in Palo Alto Bring your own laundry Details below
English
@darreljlewis1 @RameshNivedita If you’re low IQ, then you’re low IQ
That’s the tweet
English
@lightninglu10 @RameshNivedita I read hoping it was going to be interesting. Turns out if you suck at managing change, you suck at AI. That’s it, that’s the whole article.
English
If you’re still writing code / watching code be written, you’re 6 months behind
If you’re still reviewing code, you’re getting lapped
If you’re still running a dev server, you’re so out of the game that your competitor has run circles around you
Happy building ✌️
English
@prateeks PDFs work great but web pages don’t? Brother do you know that AI sucks at reading pdf’s?
A whole business Reducto exists cuz AI is terrible at deciphering pdf
English
Founders, when you share your decks with investors, please share formats that are easier for humans and AI to work with. It is a good assumption that the investor you are reaching out will have some AI processing step in their workflow.
PDFs work great!
The docsend, gamma and other web formats create friction for the consumer of your deck and do not add much in terms of experience.
English
If you want an intro to the speedrun team, hit me up! (Dms open)
andrew chen@andrewchen
ok - dropping big dates/news for a16z speedrun: - starting TODAY, founders can apply for the 2026 program that runs July 27 to Oct 11 in SF here's the link: speedrun007.a16z.com/ac - we will be investing up to $1M and funding 70+ companies over the next few weeks - But there's also $5M in credits/tokens/etc from AWS/GCP/Open AI/Azure/NVIDIA/Deel/Stripe/etc. You'll also work with our amazing operating team (GTM, talent, brand, people, and more), and join our community of elite founders - we offer a Global Founders Program for international founders, to help with visas, banking support, relo recommendations - yes you can be solo (but better if you're further along, and have built a team). No you don't have to have an idea yet. Yes you have to know how to build (even if you're not technical) - Also, in other news: speedun is officially moving full-time to SF. (prev it alternated SF/LA) this is for all the obv reasons - we've continued to have an insane lineup of speakers, including the founders of Carta / DoorDash / Twilio / Figma / Zynga / Airtable / Twitch / and of course, lunch/dinners with Marc/Ben alongside a16z team - and much more - the deadline for applying is May 17!
English
PSA: don't put secrets you actually care about in Vercel to begin with.
Anything prefixed NEXT_PUBLIC_ is in every visitor's browser by design.
Everything else is "private" only as long as your host is. And you really shouldn't be running serious backends on Next API anyways
Theo - t3.gg@theo
I have reason to believe this is credible. If you are using Vercel, it’s a good idea to roll your secrets and env vars.
English
@MatthewBerman We built this with codepress.dev/terminal
Full worktree / workflow isolation so you can work with as many agents as you want (we often do 10 at a time)
English
How are people running multiple agents at the same time? I’ve tried separate worktrees but things still get messy. I want separate environments for every agent thread. How can I accomplish this locally?
English
The best founders to invest in are the ones who don't want our investment.
English
