jordim

another gem of a resource to learn harness engineering

I’ve always believed the No.1 application of AI should be to improve human health. That work started with AlphaFold, and now at @IsomorphicLabs with the mission to reimagine drug discovery and one day solve all disease! We are turbocharging that goal with $2.1B in new funding.

"Algebrica" is a free and open mathematical knowledge base. All entries are progressively being released in Markdown format on GitHub for anyone who wants to study mathematics freely and openly. Alongside the texts, the individual SVG illustrations are also made freely available. They are minimal, mathematically accurate, and designed to be easily reusable in notes, lecture material, or educational resources. Since they are vector-based and code-driven, they can also be modified or improved simply by editing the source. Another step toward making the knowledge base more open, transparent, and genuinely useful over time.

Interesante lectura

I'm 22 years old and Claude Code is deteriorating my brain. Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me. In convos with a couple of friends, it's been a point that's been brought up pretty frequently. None of us feel as sharp as we used to. I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot. P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless

Its the beginning of the end of subsidized AI subscriptions. GH Copilot is moving to usage-based billing, as has Claude (for business customers.) Fair to assume more will follow. I expect this change will also be a great boost for open models - cheaper, and pretty good already

USING Claude Opus 4.7 TO CENTER A DIV

recommended reading. > The juniors who should be learning right now are either not being hired or developing what a DoD-funded workforce study calls “AI-mediated competence.” They can prompt an AI. They can’t tell you what the AI got wrong. techtrenches.dev/p/the-west-for…

Si trabajas con IA / Agentes / Desarrollo Software, este canal esta francamente bien. @aiDotEngineer" target="_blank" rel="nofollow noopener">youtube.com/@aiDotEngineer

OVERRATED: running tons of agents in parallel; working on too many things at once; perpetual context-switching; opening lots of low-quality PRs that may never land. UNDERRATED: using one or two agents at a time; focusing on the task in front of you; thinking deeply; finishing stuff; making your code works in prod.

When I spend 1M tokens and the <div> still isn't centered

Esto es real? 😅

:(

This, by the way, is what top tier programming looks like today You are using codex, because it 100xes your output. But you *must* understand what the computer is doing. You *must* understand *everything*. There is no other way

One of the many reasons we need real competition. Two large labs is not enough and we need to ensure we have competitive open models.

@mpampols Estic en mode hooligan amb Cloudflare. Et tinc que ensenyar el que estem montant al curro per desplegar ‘’mini agents”. Workers / Durable Objects / R2 / Pi 🔥🔥🔥. PD: puto tebas

@jordim Sona bé, però crec que no ajuda a resoldre el problema de base. Em sembla una nyapa. I més vendor lock-in.

🤩

It's kind of crazy how much of the way we've been designing Workers over the past 9 years unexpectedly turns out to be so relevant to AI and agents. Durable Objects and lightweight isolate sandboxes are obvious big things. But there are subtler things. Consider "bindings". In Workers, our environment (`env` object) doesn't just contain strings. It can contain live objects, which we often call "bindings". For instance, a Workers KV binding is a live object representing a Workers KV storage namespace. Once you've configured it, you can just do: let val = await env.MYKV.get("foo") await env.MYKV.put("foo", "new value"); Notice: There's no connection string. No secret token that you have to pass to talk to your KV namespace. The Workers Runtime handles it for you. You just get an already-initialized client object, on which you can call methods. You can still do everything you want to do. But you know what you can't do? Leak the secret token. Because there isn't one. A KV namespace binding fundamentally cannot be "leaked" because it's not bytes. But over the years, a lot of people have questioned whether this really mattered. I've had people inside and outside the team say: "Why are you so weird, Kenton? Yeah sure it can't leak but now I have to learn this new way of thinking about things. No other runtime works this way so writing portable code takes extra work. I'd rather just stick to what I'm used to, and anyway I know better than to leak my environment variables." Well, now we have AI agents writing the code and... suddenly everyone is worried about agents leaking keys. People are creating convoluted schemes to intercept the outbound traffic and inject keys in a proxy, or trying to issue very-short-lived keys so that if the agent leaks them the window of attack is short. Ahem. Welcome, folks! We solved this 8 years ago! Here's an old blog post -- written when I personally was still very much Not Thinking About AI -- which seems so much more relevant now: blog.cloudflare.com/workers-enviro…

So basically 33% more tokens with the new Opus 4.7 tokenizer. That's one chonky API revenue increase, while keeping token prices "the same".

No acabo de entender la necesidad de ir a por el último modelo de IA cuando versiones anteriores funcionan de maravilla para según qué tareas.