Lorenzo Belli

Projects are now available in Cowork. Keep your tasks and context in one place, focused on one area of work. Files and instructions stay on your computer. Import existing projects in one click, or start fresh.

🚨 Breaking: Alibaba just killed the browser automation stack. **page-agent.js** — a GUI agent that lives directly inside your webpage. No Selenium. No Puppeteer. No Chrome extension. No Python backend. Just one script tag. It reads your DOM as text (no screenshots, no multimodal BS), brings your own LLM, and executes natural language commands like "fill out this form" or "click login" — right inside the page. The use cases are genuinely insane: → Ship an AI copilot in your SaaS in literally lines of code → Turn 20-click ERP/CRM workflows into one sentence → Make any legacy web app accessible via voice or natural language 12k stars. MIT licensed. Built on top of browser-use internals — but without any of the setup overhead. This is what "AI-native UX" actually looks like in practice Link in comments👇

@georgenoble/note/c-226667679?r=4y71n" target="_blank" rel="nofollow noopener">substack.com/@georgenoble/n…

This is quite an impressive experiment. Vibe-coding the entire 2030 roadmap within weeks. Obviously such a thing built in two weeks without even having the EIPs has massive caveats: almost certainly lots of critical bugs, and probably in some cases "stub" versions of a thing where the AI did not even try making the full version. But six months ago, even this was far outside the realm of possibility, and what matters is where the trend is going. AI is massively accelerating coding (yesterday, I tried agentic-coding an equivalent of my blog software, and finished within an hour, and that was using gpt-oss:20b running on my laptop (!!!!), kimi-2.5 would have probably just one-shotted it). But probably, the right way to use it, is to take half the gains from AI in speed, and half the gains in security: generate more test-cases, formally verify everything, make more multi-implementations of things. A collaborator of the @leanethereum effort managed to AI-code a machine-verifiable proof of one of the most complex theorems that STARKs rely on for security. A core tenet of @leanethereum is to formally verify everything, and AI is greatly accelerating our ability to do that. Aside from formal verification, simply being able to generate a much larger body of test cases is also important. Do not assume that you'll be able to put in a single prompt and get a highly-secure version out anytime soon; there WILL be lots of wrestling with bugs and inconsistencies between implementations. But even that wrestling can happen 5x faster and 10x more thoroughly. People should be open to the possibility (not certainty! possibility) that the Ethereum roadmap will finish much faster than people expect, at a much higher standard of security than people expect. On the security side, I personally am excited about the possibility that bug-free code, long considered an idealistic delusion, will finally become first possible and then a basic expectation. If we care about trustlessness, this is a necessary piece of the puzzle. Total security is impossible because ultimately total security means exact correspondence between lines of code and contents of your mind, which is many terabytes (see firefly.social/post/x/2025653… ). But there are many specific cases, where specific security claims can be made and verified, that cut out >99% of the negative consequences that might come from the code being broken.

Prediction markets are good for society

I have BAD NEWS for the perma bulls. BTC is still strengthening its bear trend. Volatility is a key metric used by quants to detect trends. BTC entered its bear market when vol spiked upwards quickly. Vol then continues to climb, meaning the bear trend is strengthening. Then vol finds a peak in the mid to late phase bear market... that's when the bear trend starts to weaken. We usually see a second or third smaller peak at the macro bottom, these peaks reflect capitulation.

long ago i did a 5hr livestream where i put claude 3.7 into a game. watch it, it gets pretty interesting. a good psychological study of claude’s mentality. i fully rebuilt the harness later on and wanted to do other models with replies with in hero’s voice but the acting abilities of the models i trained for this (sesame, orpheus) required a lot of manual review, which was the thing that has killed the motivation. there are over 11k different replies and i reviewed maybe 3k and chose which gen sounds the best in context. evidently i could never finish that project and do another stream. the moral is sometimes your quality standards stand in the way of shipping something interesting. my test run with the harness i made in a couple of days is the only thing that remains. youtu.be/5PIZ0n1gBEs

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit. My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently. So, here goes.

You can even assign different agents under the same thread 🤯 Just like slack channels, except it's occupied with agents.

JUST IN : In partnership with @Visa, Dune is introducing a Local Stablecoin Report focused on the growth of over 200 non-USD backed stablecoins worldwide. The release is accompanied by the most comprehensive institutional grade dataset on stablecoins currently available, built in partnership with @SteakhouseFi. Designed for Enterprise teams. Built for scale.

TLDR: Crypto has entered a new era where revenue and paying customers are now necessities Great piece by Muyao (Blockworks data everywhere)

BREAKING: The x402 “agent payments” boom is still mostly a mirage. Yes, OpenClaw, Moltbook, and agent wallet tooling are exploding across timelines. But real x402 activity is collapsing: • ~731K txns/day in December • ~57K txns/day in February • Just ~8% of prior highs The takeaway? We’re seeing the future of agent commerce… …but demand isn’t here yet.

Anthropic spun up 16 Opus 4.6 agents to build a Rust-based C compiler from scratch - and the compiler they produced was able to compile the Linux kernel 🤯 All 16 agents worked in parallel on a shared codebase without active human intervention. No compiler engineers were involved, and the entire effort cost just $20,000 in API usage. That's it! The "agent team" produced a 100,000-line compiler capable of building Linux 6.9. Absolutely insane. We are living in incredibly exciting times.

If you do not yet have a "companion coding/research agent" running locally as a dev, this guide is absolute gold from @mitchellh (creator of Terraform). It's practical, step by step & how he changed how he works (without getting overloaded or anxious.) mitchellh.com/writing/my-ai-…

NEW POST Powerful context engineering is becoming a huge part of the developer experience of modern LLM tools. Birgitta Böckeler explains the current state of context configuration features, using Claude Code as an example. martinfowler.com/articles/explo…

40M$ arbitrage opportunity explained by Polymarket Quant This is the best 30-minute read on how Polymarket actually works It explains how bots using the "Frank-Wolfe algorithm" are extracting millions $ monthly just by using math If you want to go deeper than just "YES + NO < $1" thinking, you should read it.

A must read to understand how wallets are powering the next generation of financial markets.

What if we're actually in the middle of the third golden age of software engineering? This is what @Grady_Booch sees happening. If you are anxious about the state of the industry, you want to watch/listen to Grady's longer-term perspective and stories. Watch the full episode here: 00:00 Intro 01:58 The first golden age of software engineering 18:59 The software crisis 33:01 The second golden age of software engineering 42:21 Y2K and the Dotcom crash 45:47 Early AI 47:34 The third golden age of software engineering 51:48 Why software engineers will very much be needed 58:46 Grady responds to Dario Amodei 1:06:54 New skills engineers will need to succeed 1:10:04 Resources for studying complex systems 1:14:33 How to thrive during periods of change 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 automated code review. Join me online at the Sonar Summit on March 3rd, where I talk about practical tactics for the AI era. sonarsource.com/pragmatic/sona… • @WorkOS – Everything you need to make your app enterprise-ready. workos.com