Peter Carpenter
12 posts
Peter Carpenter
@petercarp320
Founder @ Clarix. Replacing insurance BPOs with AI agents. Pre-revenue, building in public. DMs open.
شامل ہوئے Ocak 2024
62 فالونگ4 فالوورز
There's an infinite well of things to do that could work that are of this kind
Paul Graham@paulg
@charliermarsh Sometimes they're a good reason to work on something. When people say a market is "crowded," what that often means is that there's a real problem and none of the solutions are good enough yet.
English
@Principal_ADE @garrytan Fair, but I think it’s aimed one layer off. The human isn’t in the loop at inference, they’re in the loop at eval design. Each miss becomes a permanent test the next version inherits. The labor is one-time per failure mode. What doesn’t scale is obsessive users, not the method.
English
@petercarp320 @garrytan I do think this is true which is why it makes me so skeptical on the general scalability
English
@dflieb Right. Compute makes the answers cheap. It was never the answers that were scarce, it was knowing which questions are worth asking. You can't brute-force taste.
English
Thought experiment: if every company suddenly had infinite free compute, what new products would emerge?
My take: with very few exceptions, not much would change. The bottleneck is figuring out what people want, and it’s not so easy to apply compute to solve that.
English
@garrytan “Anthropic and OpenAI are the last startups” is like saying power plants made every other company pointless after electricity. The model is infrastructure, not the finish line. Distribution, trust, and the last mile of a real user’s problem still need founders.
English
Oh man, this is going to be a very tired argument we are going to have for the next 5 years
Garry Tan@garrytan
The real AI whitepill is: There will always be a market for translating what the 200 IQ people and agents make down to everyone else
English
Conductor + GStack + GBrain + Claude/Codex
Thats all you really need. It is a understatement to say this is a must. Being able to have multiple workspaces work and think like they have a hive mind is amazing. Thank you @garrytan!
English
@ApolloAtomics Very excited for the future. Can't wait to see you guys be part of it. I've been talking about this and waiting for this to happen.
English
Building the modern nuclear company.☢️
Y Combinator@ycombinator
.@ApolloAtomics builds the most compact nuclear reactors with the highest uptime and a deployment time of less than 24 months. Apollo took the pressurized water reactor technology that already powers 80% of the world’s nuclear plants and flipped one part, the steam generator, to make the plant an order of magnitude smaller without compromising power. Congrats on the launch, @AssilHalimi & Drew! ycombinator.com/launches/QXj-a…
English
@garrytan Any plans for multi-tenant readiness on the roadmap? Would love to see it become a first-class part of GBrain.
English
Early review of GBrain - I am working on it day-to-day, dropped more than 20 PRs in the last week, so it is a young codebase growing quickly and changing. This is great feedback.
GBrain getting better every day
vectorize.io/articles/gbrai…
English
@dkundel I had to create a DIY version of this for when I was away from my computer. Now i don’t have to worry about that
English
To be clear this specifically enables "computer use" on your locked Mac. It also displays on your screen when Codex is controlling your Mac.
It's a really cool feature and the team had to solve some interesting challenges to enable it!
OpenAI Developers@OpenAIDevs
Codex anywhere and everywhere, all the time. Now your Mac doesn’t have to be unlocked for Codex to use your computer. From your phone, Codex can securely use apps on your Mac, even when the screen is off and locked. #locked-use" target="_blank" rel="nofollow noopener">developers.openai.com/codex/app/comp…
English
Heads up: in the Codex app you might have to ask Codex to enable the feature.
> Run `codex features enable goals`
Then restart the app. We will have a fix rolling out soon to properly enable it by default.
OpenAI Developers@OpenAIDevs
🥅 /goal has graduated from an experiment—for tasks big and small, Codex gets your work done. Use goal mode in the Codex app, IDE Extension, or CLI to give Codex a specific milestone, and it will keep working until it gets there, even across hours or days. You can check in and steer, and even pause Codex along the way. Pro tip: start side chats to understand the work that has been done so far without having to interrupt the main task. #goal-mode" target="_blank" rel="nofollow noopener">developers.openai.com/codex/promptin…
English
@OpenAIDevs Question here / Help needed. I have updated my app but I currently cant do the /goal commands. Its just saying "No commands". I have just recently switched over to codex for dev work so I may be missing something. Any help wanted!
English
It’s Codex Thursday, and yes, we have updates for you.
First up: Appshots, a new way to bring the context of what you’re working on into Codex.
On your Mac, press Command-Command to attach your app window to a Codex thread. Codex gets both a screenshot and text from the window, including content beyond what’s visible onscreen.
Appshots are available across plans on Mac, with enterprise access coming soon.
English
@effyyzhang My biggest concerns atm is that Managed Agents don’t fully match GCP’s strengths in regulated environments or massive-scale operations. We are about to sign some big enterprise clients, and we really need to have per-client/tenant data isolation. I would love to talk about this
English
Founder friends ask me: why Claude Managed Agents vs. X, Y, Z?
Beyond feature fit, every integration has a cost. Picking a product is picking a long-term partner. You're betting on who listens, who supports you, who ships faster than your roadmap grows.
A few weeks after we announced CMA, today at Code with Claude we launched multi-agent, outcomes, webhooks, and Dreaming. So much more coming.
platform.claude.com/docs/en/manage…
English