Tweet épinglé
anna
960 posts
anna
@nevm_a
growing @withoneai | automating GTM for tech startups | founder @ Socially Produced
San Francisco, CA Inscrit le Şubat 2018
211 Abonnements475 Abonnés
@chiefy or you can use smth like @withoneai so there’s only one cli for everything including payments & you don’t need to mange memory or re-auth
English
a very simple agentic memory system you can build yourself does this. cloudflare tunnel, vultr vps, tailscale, use Rust + Axum, google workspace cli for auth- you can get minority report style custom internal apps up with a few prompts - payments part is tricky
Andrej Karpathy@karpathy
When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc... I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!
English
@Lwrncma i think if you try @withoneai this set up time will go down to minutes
English
100% agree with this, the amount of API connections, account registering and set up work takes way more time than the actual MVP of several projects I've worked on recently.
Andrej Karpathy@karpathy
When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc... I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!
English
@tobiasjames_eth check out @withoneai I had a super easy time with it as a non-developer
English
This is the problem I’ve faced for the past week or so. The idea and code are the easy part. Connecting everything together that I’ve been planning for the last 6 months is the face-melting part. For anyone who knows what they’re doing building apps, it’s probably easy to orchestrate, but for me as a vibe coder with no experience in building or designing apps, it’s my toughest challenge yet.
Andrej Karpathy@karpathy
When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc... I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!
English
@levelsio @MarceloRet41877 @StevieZollo see what @katibmoe launched two days ago cuz it literally would solve all of your set up issues in a matter of minutes (there’s stripe and hundreds of other apps in a single cli w enterprise-level auth security)
English
@MarceloRet41877 @StevieZollo No I just copy pasted it into Claude Code
I used Photo AI's Stripe key
English
✨ To prove my friend @StevieZollo (who's visiting me in Brazil) you don't need an idea, or even a lot of time these days to ship a little app that might make money
I took the top idea from IdeasAI.com:
"A startup that uses AI to generate personalized bedtime stories for kids based on their interests, family photos, and daily activities, delivered via a voice app.
(❤️ 110 likes, 3 days ago)"
So I copy pasted it into Claude Code and asked it to build it
The first version of course didn't work, and I had to tell it some endpoints didn't work properly but then it fixed it
The bedtime stories are generated by @xAI Grok 4.1, then sent to TTS with @GoogleAI Gemini and payment with @Stripe Checkout
Total time from start to live: 24 minutes
@levelsio@levelsio
Some nice new ideas upvoted by everyone today With the new AI models + human upvoting and downvoting there might actually be good ideas here for people to build startups from Possibly...
English
@TukiFromKL if only this was solved 2 days ago by an open-source database of agentic integrations & a single CLI & auth for all major apps…oh wait… x.com/katibmoe/statu…
Moe@katibmoe
Introducing One. The simplest way to connect and monitor AI agents to hundreds of apps. And we’re open-sourcing the world’s largest integration database powering it: 47,000 agentic actions across 250+ apps. RT + comment “One” for access & 1M free API requests/month.
English
🚨 do you understand what Karpathy just said..
the guy who co-founded OpenAI.. led AI at Tesla.. one of the best engineers alive..
built an app with AI.. and said the code was the easy part..
the hard part was Stripe.. auth.. DNS.. databases.. deploying it.. connecting 15 different services that all have different dashboards and different docs and different billing pages..
AI can write your entire app in 20 minutes.. but it still can't click "confirm email" on Vercel..
so the thing that's "replacing developers" can't do the thing developers actually spend 80% of their time doing..
vibe coding didn't kill software engineering.. it just proved that coding was never the job.. the job was dealing with the mess around the code.. and that mess is still 100% human.
Andrej Karpathy@karpathy
When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc... I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human. It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!
English
@karpathy Yep. Either we build a centralised connector that follows same protocol easy for AI agents to connect.
Or build a mega tool that covers most business tools with a single api access
English
When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make it real, the DevOps: services, payments, auth, database, security, domain names, etc...
I am really looking forward to a day where I could simply tell my agent: "build menugen" (referencing the post) and it would just work. The whole thing up to the deployed web page. The agent would have to browse a number of services, read the docs, get all the api keys, make everything work, debug it in dev, and deploy to prod. This is the actually hard part, not the code itself. Or rather, the better way to think about it is that the entire DevOps lifecycle has to become code, in addition to the necessary sensors/actuators of the CLIs/APIs with agent-native ergonomics. And there should be no need to visit web pages, click buttons, or anything like that for the human.
It's easy to state, it's now just barely technically possible and expected to work maybe, but it definitely requires from-scratch re-design, work and thought. Very exciting direction!
Patrick Collison@patrickc
When @karpathy built MenuGen (karpathy.bearblog.dev/vibe-coding-me…), he said: "Vibe coding menugen was exhilarating and fun escapade as a local demo, but a bit of a painful slog as a deployed, real app. Building a modern app is a bit like assembling IKEA future. There are all these services, docs, API keys, configurations, dev/prod deployments, team and security features, rate limits, pricing tiers." We've all run into this issue when building with agents: you have to scurry off to establish accounts, clicking things in the browser as though it's the antediluvian days of 2023, in order to unblock its superintelligent progress. So we decided to build Stripe Projects to help agents instantly provision services from the CLI. For example, simply run: $ stripe projects add posthog/analytics And it'll create a PostHog account, get an API key, and (as needed) set up billing. Projects is launching today as a developer preview. You can register for access (we'll make it available to everyone soon) at projects.dev. We're also rolling out support for many new providers over the coming weeks. (Get in touch if you'd like to make your service available.) projects.dev
English
@Jesse_Anglen @karpathy take a look at @withoneai - it connects to stripe, github, etc and takes less than a minute to set up
English
Built a full deployment agent last fall and can confirm. The code gen part worked by day 2. Spent another week teaching it to navigate Stripe's sandbox/prod key rotation, Vercel's project linking flow, and GitHub webhook setup. Most of those APIs exist but weren't designed to be called without a human in the loop double-checking each step.
English
A guy in Hampton built a $5M/year tax software company with his wife as co-founder.
@ChKashifAli studied accounting and worked as a journalist for 6 years (including at the WSJ).
Then he taught himself to code and worked at Adobe for 3 years.
He builds two failed startups.
Then comes TaxGPT, an AI accounting software tool (he coded it in 2 days).
3 years later:
$5M ARR
6x year-over-year growth
135% net retention
50 employees
$6M raised (they went through Y Combinator)
Kash runs the whole thing with his wife Isabella as co-founder.
English
@nevm_a @hthieblot where are you in the world right now ? if you're in the same area you can take it in the mean time, I dont mind
English
Founders: What's the one thing you do to relax?
For me, it was always playing video games 🎮
English
@quinnslcm @Shwinnabego protein ice cream is ripping in my neighborhood. this one guy built the brand in hawaii, then opened second location in sf, the line is out of the door
English
@ShukBonaparte @hthieblot i mean if you're not using it I'll take it hahah. I need to finish assassin's creed unity
English
@nevm_a @hthieblot What I haven’t touch my ps5 for months 😭
English
@ShukBonaparte @katibmoe I'll dm you the link in a second! I think the team hit a DM limit so it's taking them a little longer to get back to people
English
Introducing One.
The simplest way to connect and monitor AI agents to hundreds of apps.
And we’re open-sourcing the world’s largest integration database powering it: 47,000 agentic actions across 250+ apps.
RT + comment “One” for access & 1M free API requests/month.
English
MOA is actively working with:
- the biggest apparel brands in the USA
- the biggest festival companies in the world
- the biggest tech companies
- the biggest experiential production companies
If you sound like one of the above, we’d love to work with you:
magnumopus.agency/workwithus
English
Respectfully nobody comes even close to us
Ben Tossell@bentossell
merch gifts have gone up a level ty @OpenAI
English
The person who builds PayPal for agents will be an instant billionaire.
English
@khemmapich @katibmoe @workserai DMing you now! but you have to come back and tell us how it went :)
English
@katibmoe One ! Interesting tool, I will try on my ai product @workserai
English
@robinmaben @katibmoe king 👑 the engagement is for a good cause - now more people can see and benefit from One :)
English
