传声·当日

This is going to be common from here Brave new world Prompters of the world unite https://t.co/rtuwOGiEzQ

Ultimately the golden age of abundance will be this kind of tech built and deployed 1000x https://t.co/ezuSdcjE3w

By evals I mean literally tell the agent: given what we discussed about what we are doing and why and what happened, use three different frontier models to look at inputs and outputs of your skill file calling the code, and rate it on effectiveness. Why isn’t it a 10? How could it be made to be so? Run this a few times and you will be surprised how fast it gets astonishingly better And since it is in a skill file plus code with evals (LLM as judge) and unit tests, it stays better forever

It's not everyday you get to host someone who's been to space. I'll be chatting with Group Captain Shubhanshu Shukla @gagan_shux at @spc_india. Fighter Pilot. Astronaut. First Indian on the ISS. Incredible guest. Register to attend, BLR, May 28. https://t.co/D0fUyBRgfZ

Codex is very good. I'm especially impressed by how it uses the browse to test its own work. But any design related / frontend tasks, Claude still wins.

You have to think of tokenmaxxing as eating crab legs at the buffet. The buffet (all you can eat AI plans) is not going to last forever so you better eat all the crab legs while you still can.

What used to feel like procrastination (building systems instead of the MVP) is now a prerequisite to ship effectively with AI agents. My number 1 lesson from @ryancarson: "We used to say just do the bare minimum to get the MVP out. Don't spend time on systems. It's literally reversed now. You have to spend a lot of time setting up your documentation. Build all that into a cron job with a skill file, and suddenly you're doing the work of 10 people." 📌 I asked Ryan how he ships 10 PRs a day, here's his answer: https://t.co/8jMGNSdHmu

The CEO of Goldman Sachs is taking the other side on the pessimistic takes on AI and jobs. If you looked at what work looked like a few decades ago and saw how much faster everything is or easier it is to produce the same thing as before - even before AI - you’d certainly have been convinced there’d be no jobs left. What happens is we constantly just demand more from everything. Instead of automating a task and delivering the same value proposition, but cheaper, we just expect more from the overall product or service. Because some players in the market decides to do more with the automation, and it raises everyone’s expectations. So those that don’t respond can’t compete. We get more financial analysis from analysts. We get much more comprehensive legal advice. We get more tailored financial services offerings. We get better software in niches we never thought we could automate. Our healthcare providers offer more tests and deeper medical advice. This just goes on and on. When you move from believing the world is static and you’ll have a better view of how jobs evolve due to AI.

I haven't written a personal blog post in over 5 years so if you see posts that claim to be written by me, they're not. I'll update if this ever changes. Maybe it should.

"Humanity, created by God in all its grandeur is today facing a pivotal choice: either to construct a new Tower of Babel or to build the city in which God and humanity dwell together." The Pope has obviously been reading @every from 2024: https://t.co/TxmwICvJ77

It’s hilarious how many people DM me every week asking “aren’t you a VC, why are you building”.. Brother, the space is moving so fast that the only way you can learn and stay at the frontier is by building. Priors need to be rethought every few months. It’s also SO much fun to explore the edges of these models and discover new capabilities that haven’t been documented yet. I also find it absurd that how can you NOT be curious and redo how you do work. We have alien super intelligence in our hands and you want to spend hours doing it the same way just because it’s comfortable? Automate or get automated is the bitter lesson we all need to learn. And have a lot of fun along the way :)

OpenClaw's dependency purge continues. Killed Sharp and Jimp. Replaced it with photon, a small WebAssembly that runs compiled Rust for image processing. 2MB vs 140MB. https://t.co/tSimX2GKwP

Folks: when you write skills, ask your agent to be token efficient, relax grammer. I see too many skills that write books in the skill description, and all that crap is loaded into every context. I wrote a skill that finds the worst offenders. https://t.co/kfaaJpxMXE

There's security, and there's clankers. https://t.co/TLA07uIEZB

Speaker 1 | 00:00 - 00:18 We are a part of this like super cycle right now and the super cycle does not last forever. And so if you're gonna pause by the super cycle, you are speeding market. Like that is what you're doing. I would ask Claude, can you go fetch the data from our bank? And then it was like, oh yeah, just log in and give me access. Speaker 1 | 00:18 - 00:36 I'm like, log in and give me a no. I will not give you access. Right away fundamentally for me that was like broke the entire thesis of it. So you give it its own machine. When I think about agents, I think of them as digital knowledge workers And to do anything as a knowledge worker, you do need a computer. Speaker 1 | 00:36 - 00:40 My argument is that every agent will need at least one sandbox, sometimes more. Speaker 2 | 00:40 - 01:11 Claire Matturk. Welcome to the MAD podcast. My guest today is Ivan Borozin, CEO of Daytona, one of the most talked about startups in agent infrastructure. If you've been hearing the word sandbox in every AI agent conversation and quietly wondering what it actually means and why it suddenly matters, this episode is for you. We go from first principles, why does an agent need a computer at all, all the way to the deep technical end, why Daytona had to throw out Kubernetes and write their own scheduler, and why a global CPU shortage might be coming faster than people think. Speaker 2 | 01:11 - 01:34 Ivan also unpacked the full agent stack as he sees it, models, sandboxes, tools, MCP, memory, orchestration, and where each piece is heading. Along the way, Ivan shares some really interesting lessons on go to market and distribution for technical founders that he has learned through sixteen years building developer tool startups. Please enjoy this conversation with Ivan fr