Sabitlenmiş Tweet
Fred Oliveira 🧠
15.8K posts
Fred Oliveira 🧠
@f
perpetual 0 to 1 machine, working towards better AI futures. @lisbonai_ @capitalfactory @snyksec @gumroad @techcrunch @oreillymedia
Katılım Eylül 2006
882 Takip Edilen134.1K Takipçiler
@blast_hardchese @charliermarsh doesn't feel like a good characterization of the current moment for Github.
English
@charliermarsh peak design. Boring is reliable, reliable is fast
English
@dwarkesh_sp look Dwarkesh, you can't be bringing back clips from arguably your best set of episodes without getting Carl on again. For a blackboard session, if I can one-time-dealer this one.
English
“Why are you putting your foot *there*, and not *over here* where I am?” they shout incessantly at the tightrope walker
English
@jackclarkSF @karinanguyen just in case you were done with the thread - and apologies if not - the direct link was missing:
importai.substack.com/p/import-ai-45…
English
@karinanguyen My whole experience doing this project was finding endless "up and to the right" graphs at all resolutions of AI R&D, from the well known (e.g., SWE-Bench) to more niche (like those above). It's a fractal, but at all the resolutions you see the same trend of meaningful progress.
English
I've spent the past few weeks reading 100s of public data sources about AI development. I now believe that recursive self-improvement has a 60% chance of happening by the end of 2028. In other words, AI systems might soon be capable of building themselves.
English
Jack's newsletter (we still call them that in this household) is one of the clearest, most insightful resources out there for people trying to navigate both where we are now and the space of possible futures. Highly recommended reading.
Jack Clark@jackclarkSF
I've spent the past few weeks reading 100s of public data sources about AI development. I now believe that recursive self-improvement has a 60% chance of happening by the end of 2028. In other words, AI systems might soon be capable of building themselves.
English
absolutely absurd if these numbers pan out.
insane opportunity if these numbers pan out.
The Information@theinformation
xAI’s GPU fleet is running at about 11% utilization, exposing how hard it is for AI labs to fully use expensive Nvidia hardware. Read more in our AI Agenda newsletter: thein.fo/4cHRjWI
English
@steveruizok deviantart top makers from the early 2000s and you have it. People who know how to hand mask and airbrush in photoshop. The real pixel degens.
English
Who even makes UI like this? How would one even hire for this?
English
@steveruizok I can *absolutely* feel how the buttons work just by looking at the screenshot
English
Fred Oliveira 🧠 retweetledi
Very wrong, very dangerous
You want your APIs to do the exact same thing, every time
AI is great at many things; reproducibility is not one of them
Naval@naval
AIs replace UIs and APIs.
English
@jayfarei Most "build your own AI agent" projects die the same way. Two weeks of setup, then you lose steam before the agent does anything real.
Flue treating the sandbox as a primitive is what collapses it to 43 lines. Bottleneck stops being plumbing and becomes the prompt design.
English
This is quite beautiful, 43 lines and you have your own code agent in a sandbox at POST /agents/<agent-name>/<id> 🤩
fks@FredKSchott
Introducing Flue — The First Agent Harness Framework Flue is a TypeScript framework for building the next generation of agents, designed around a built-in agent harness. Flue is like Claude Code, but 100% headless and programmable. There's no baked in assumption like requiring a human operator to function. No TUI. No GUI. Just TypeScript. But using Flue feels like using Claude Code. The agents you build act autonomously to solve problems and complete tasks. They require very little code to run. Most of the "logic" lives in Markdown: skills and context and AGENTS.md. Flue is like Astro or Next.js for agents (not surprising, given my background 🙃). It's not another AI SDK. It's a proper runtime-agnostic framework. Write once, build, and deploy your agents anywhere (Node.js, Cloudflare, GitHub Actions, GitLab CI/CD, etc). We originally built Flue to power AI workflows inside of the Astro GitHub repo. But then @_bgiori got his hands on it, and we realized that every agent needs a framework like Flue, not just us. Check it out! It's early, but I'm curious to hear what people think. Are agents ready for their library -> framework moment?
English
@mattzcarey @pcbo @deloreyjmi @avenceslau @goncalossilva lovely to meet you, Matt. Pretty sure we’ll meet again very soon 🙌
English
my slides for agents day
agents-day.mattzcarey.workers.dev
was every fun to hang with @pcbo @deloreyjmi @avenceslau @f @goncalossilva and crew
English
English
The duality of pool: using pool in Zed as an ACP server (left) to develop pool ACP client (right).
English
Starting to map the graph for a founding engineer at Perfloop.
Looking for real systems depth - perf, infra, observability, AI infra, devtools, databases, runtimes - plus extreme agency, product/architecture judgment, and native agentic building.
Europe / near-Europe overlap preferred.
English
