applied ai @happyrobot / prev. co-founder & cto @gizatechxyz / prev. scaling prod ml infra @adidas @bbva / tech+optimism
Madrid
Joined August 2011
- Tweets925
- Following1.5K
- Followers2.3K
- Likes4.9K
Fran Algaba retweeted
How do always-on, proactive agents like @Bot work?
Watch my lecture at Stanford CS146S:
2:35 How we got here
6:13 What changed in the models
10:06 Inside an always-on agent
18:07 The harness
27:26 Context engineering
34:26 Where this is going
Fran Algaba retweeted
The future of FDE work seems closely related with all work around evals/posttraining/RL envs.
FDEs are effectively responsible for the following:
1. Define the business problem.
2. Codify the business problem into an eval rubric and environment.
3. Hillclimb the environment and output an agent/agentic workflow that solves the business problem.
Right now the process of (3) is quite manual - historically FDEs spend hundreds of hours creating bespoke software/workflows that solve the problem.
But assuming intelligence is abundant, they can effectively offload (3) to some automated optimization process. This includes RL on the model layer, and using Claude Code/Codex to optimize the harness/workflow.
Then the FDE responsibility shifts from implementing the task to defining the right goals and outcomes. In other words, they have access to /goal, and their job is more around making sure the goal, environment, and evals are correct vs. the tactical implementation details.
Fran Algaba retweeted
Ryan Dahl just launched celld: self-hosted, distributed Durable Objects.
One SQLite database per cell. S3-compatible storage. No separate database cluster or control plane.
I looked at the architecture, tradeoffs, and where I’d use it:
flaviocopes.com/celld/
Fran Algaba retweeted
recommended reading. in a few systems i built over the past 2 years i ended up with this flow for a given task:
- start with full inference for all steps, observe behaviour, judge correctness
- find inference steps that can be replaced with deterministic steps
eventually, most inference goes away, leading to more stable yet capable systems that can do much more than deterministic systems alone.
Wrote about this intuition a while back. Really hard to scale as each problem has an specific approach that will make it reliable. Hopefully we can discover good patterns!
davidgasquez.com/reliable-un…
Fran Algaba retweeted
someone hit me up about the new "claude dynamic workflows" feature, claiming "see, multi-agent works"
But really, the launch of this feature proves the exact point that I made back in June of 2025, along with @walden_yan, @tobi, @karpathy, and many others:
Deterministic workflows orchestrating small agent loops beats non-deterministic multi-agent or "agent soup" systems every dang time
everything is context engineering
Fran Algaba retweeted
Introducing Assay, risk markets for onchain finance.
Every DeFi yield has a risk price. The problem is that the market cannot see it.
Assay makes that risk tradeable through markets for specific onchain conditions like depegs and rate spikes resolved from chain state.
Fran Algaba retweeted
pi has an even shittier website now. You're welcome.
buildwithpi.ai
Fran Algaba retweeted
🆕 Claude Agent SDK [Full Workshop]
youtube.com/watch?v=TqC1qOfi…
For our first big drop of the year, excited to bring you @trq212's full 2 hour workshop covering all of @AnthropicAI's agentic SDK (formerly known as Claude Code SDK).
By far the most popular workshop of AIE CODE! Now published online for free (sorry for AV/delay issues)... long story
![Claude Agent SDK [Full Workshop] — Thariq Shihipar, Anthropic](https://pbs.twimg.com/card_img/2113161863437725696/pC32ufEh?format=jpg&name=800x419)
Fran Algaba retweeted
Announcing the Beta release of ty: an extremely fast type checker and language server for Python, written in Rust.
We now use ty exclusively in our own projects and are ready to recommend it to motivated users.
10x, 50x, even 100x faster than existing type checkers and LSPs.
ALT Comparing ty to Pyrefly, Pyright, and mypy on home-assistant.
Fran Algaba retweeted
How to Keep Winning
amasad.me/keep-winning
Fran Algaba retweeted
Sending money to friends should be as easy and private as sending a message.
Our developers imagined what Bitcoin inside Signal could feel like. We integrated Cashu into the iOS and Android Signal apps, delivering a beautiful experience that protects user privacy end to end.
Fran Algaba retweeted
Not just a streamlined way of using Arma but also your gate to onchain market analytics for stablecoins.
It launches as one of the featured agents in the front page of @baseapp taping to millions of users to offer the best optimized stablecoin yield 🟦
Your personal agent is now live inside your @baseapp.
Until now, wallets were places to 𝐡𝐨𝐥𝐝 assets.
Today, they become places where assets are 𝐨𝐩𝐭𝐢𝐦𝐢𝐳𝐞𝐝, 𝐚𝐥𝐥𝐨𝐜𝐚𝐭𝐞𝐝, 𝐚𝐧𝐝 𝐠𝐫𝐨𝐰𝐧. 𝐀𝐮𝐭𝐨𝐧𝐨𝐦𝐨𝐮𝐬𝐥𝐲, 𝟐𝟒/𝟕.
