Anthony Wu

Anthropic shouldn’t do this and doesn’t have to Would be great if it stopped

GitHub these days

> stripe projects catalog cloudflare let your agent sign up for Cloudflare, buy a domain and deploy to production, all on its own blog.cloudflare.com/agents-stripe-…

Starting today, agents can now be Cloudflare customers. They can create a Cloudflare account, start a paid subscription, register a domain, and get back an API token to deploy code right away. cfl.re/4sY0Uxn

@Mugilan_SS @OpenAI It’s the small things. When we designed this the tradeoff was between a good experience or optimize for margin and not allow to draw more usage than you technically have. We chose to optimize for the experience as it’s really annoying to have your agent interrupted midway.

I made as much money selling half my small investment in Rappi in 3.5 years as I did from 8 years of grinding my previous startup. It was a little depressing how one investment that took relatively little effort amounted to the same as 8 years of a hard startup.

OpenClaw - the agentic software spreading like wildfire - was built on top of Pi, a minimalist, self-modifying agent. I sat down with Pi's creator, @badlogicgames and longtime Pi user (+ the creator of Flask) @mitsuhiko to talk Pi, and their (very grounded!) takes on building with AI. Timestamps: 00:00 Intro 07:30 How Mario, Armin, and Peter Steinberger met 15:15 How 30 dev teams use AI agents: learnings 21:50 The importance of judgment 24:26 Challenges when non-engineers write code 28:30 Downsides of over-automation 32:18 Pi 48:09 OpenClaw + Pi 50:54 “Clankers” 57:32 Open source and AI 1:00:22 Complexity as the enemy 1:02:50 Building an AI-native startup 1:11:52 “Slow the F down” 1:16:40 MCPs vs. CLI 1:25:03 Predictions and staying up to date • YouTube: youtu.be/n5f51gtuGHE • Spotify: open.spotify.com/episode/1fDw9c… • Apple: podcasts.apple.com/us/podcast/bui… Brought to you by: • @statsig  – ⁠ The unified platform for flags, analytics, experiments, and more. statsig.com/pragmatic • @SonarSource  — The makers of SonarQube, the industry standard for code verification and automated code review. Try it out for yourself. sonarsource.com/plans-and-pric… • @WorkOS  – WorkOS gives you APIs to ship enterprise features – SSO, directory sync, RBAC, audit logs – in days, not months. Visit WorkOS.com to learn more. --- Three parts I found especially interesting in this discussion: 1. New trend: AI makes it harder for senior engineers to reject pointless complexity. Historically, senior engineers kept software complexity at bay simply by saying “no” a lot. But Armin observes that these days, more junior engineers and product managers deploy agent-scripted counterarguments when a senior colleague kicks an idea to the curb. This makes decision-making exhausting, and more bad ideas make it into production as a result. 2. It should be MUCH easier to build specialized tools for specific tasks. Different projects need different harness types because, as Mario points out, the same hammer is not ideal for every single construction job. As such, Pi is built with the goal of allowing the creation of specialized harnesses. It can modify itself so that a user can create the bespoke harness needed for any task. Mario believes it’s a preview of how self-modifiable software might look in the future. 3. Automation bias is one of the biggest risks of working with AI agents. Once devs confirm that an AI agent can produce acceptable code, they start to review its output less often, even though agents can – and do! – produce slop. Mario advises being far more sceptical with agents, and cautions that the quality of their output isn’t guaranteed, however well they performed previously.

People of pi.dev Cloudflare Workers AI release. We want to see forking company and triangle company battle it out to the death. So since we had Vercel Gateway in pi for quite a while, we now have merged a PR that adds CF Workers AI as well. CF AI Gateway yet to come.

The vibes are good!

New work with @AlecRad and @DavidDuvenaud: Have you ever dreamed of talking to someone from the past? Introducing talkie, a 13B model trained only on pre-1931 text. Vintage models should help us to understand how LMs generalize (e.g., can we teach talkie to code?). Thread:

AI leaders need to talk more about the incredible positive upside of AI, not the conflated downsides (yes, I'm looking at you Dario). $GOOGL $NVDA THANK YOU to Google's Amin Vahdat and Jeff Dean for their inspiring visions on what AI will enable. The video clip below is a MUST WATCH. Also: “No matter what, it’s going to take a lot of compute” It would be the dumbest thing ever to overregulate and cripple AI progress based on false, misleading AI doomer narratives.

An easy way to get a team engaged with AI is just to build the thing you are talking about in the meeting during the meeting using Codex or Claude Code. At worst, it fails in ways that can be constructive. At best, you built the thing and the meeting topic shifts forward a month

all the best programmers i know spent effort testing the practical limits of AI. they identified a sweet spot that delivers productivity improvements while retaining control of design, implementation, and cognitive ownership so they could remain responsible and accountable.

Looking at the traffic dashboard for Codex just now, it would be scary if we didn't have a lot more compute coming online in the coming weeks. All according to plan fortunately.

The only people who believe any of this are non-coders. I tried to build a game (an area I’m an n00b in.) The results are amusingly disastrous - I never before coded a decent game. But I’ll crack out backend services w AI rapidly - because I coded dozens of them before…

this is neat! free search for people of pi (within rate limits)

Everyone is slowly coming to this realization, and I assure you, no one is running multitudes of agents overnight. No one that is doing anything of substance at least. There _are_ people pretending to be scientists, or fully caught up in their drug infused AI overdose, that think their slop machines are changing the world. They're not tho, and they're just wasting a bunch of money and compute to create a lot of LoC that will just get thrown away. The state of the art is still "can we even one shot a production quality patch that we wont regret later", and its rarer than you'd expect based on discourse.

Those who treat humans as machines are also treating machines as humans.

Adopting Claude speak in my regular life, episode 1: Partner: Did you do the dishes tonight? Me: Yes they're done. Partner: Why are they still dirty? Me: You're right to push back. I didn't actually do them.