The second news is…. Powertools for AWS Lambda now has an official website! powertools.aws.dev/ There are countless people to thank as it took nearly 5 years to get here. Special thanks to @IsenbergRan @djfurman4tech and all public reference customers #aws #serverless

RT @antoniotabet: A família miliciana odeia tanto mulher preta, que resolveu atacar Nossa Senhora Aparecida!

How are you structuring adversarial reviewers for verification loops? Prompt or got predefined reviewers per domain like security, language, db, outcome verifier etc? I’ve got the latter and while it worked well, models advanced, and now I’m rethinking its efficiency atm

The models are also very good at architecture only if you can see it. "The beauty is in the eye of the beholder." It's not I disagree - I just want to highlight "the nature of problem". An operator's skills and competence is the ceiling for LLM. Why? ⬇️

Removing *all* unit tests because of agents take is mass hysteria

This is a highly inconvenient state of affairs: Fable > Astra Codex > Claude Code

Jev

Bend 2 is here! It is a new programming language that blocks AI mistakes via *proof checking* - the same technique big AI labs used to solve open math problems, like Navier-Stokes. It is also very fast, and runs on GPUs. Watch the video. Link in the comments.

New experiment: json-render + jev The future Generative UI is instant Your components, your actions, your design system Rendered in milliseconds

Jev seems ideally suited for this. Have AI constantly evalulating tiny in-progress chunks of work and deciding if it should send more more or less production traffic

Here's a 45-second TL;DR on Jev. I find the core idea beautifully simple, but the video made it really hard to understand. Hope you find it helpful.

Agentic coding in 2026

Que vídeo espetacular, que aula sobre o escândalo do Banco Master! Sinceramente: quem assiste a isso e ainda insiste na narrativa tosca de que o esquema não começou no governo Bolsonaro, ou age por má-fé ou tá com a cognição totalmente comprometida. Não tem outra explicação. FLÁVIO É VORCARO BOLSOMASTER DA CORRUPÇÃO

Okay, it took a week to get this done the right way, but it's finally all complete, my comparison of Astra and Fable 5.1 with @VulcanBench 🖖 A few things took longer here, the primary one being some updates to my benchmarking score to layer in code quality. This added 3-4 days of time, but for the right reasons. This new class of models requires a new class of benchmarks. I don't think we can just look at things like accuracy any more, we also have to look at code quality/maintainability factors. Now with VulcanBench-SWE v4, 33% of the score is code quality/maintainability. For me, and many other engineering leaders, seeing a model get a 98% on a benchmark doesn't really give us much signal. I created VulcanBench to help make decisions around model and effort level, and this means not just building evals that represent the kind of work teams give to these models, but the kind of output we expect from these models when building scalable system and working in large codebases. While I would normally share more about my thoughts, I'll let you come to your own conclusions about Astra and Fable 5.1. Both are excellent models, OpenAI and Anthropic have really created a new class of models here, now it's for us to decide if we need this horsepower for daily tasks, or just the hard stuff, and to be realistic about the quality of the output. Model card below, and if you want to do a deep dive, you can find more on the VulcanBench site here: vulcanbench.com/benchmarks/s… And of course, since VulcanBench is open source, you can review every detail of this benchmark, or even run it yourself. The GH repo is here: github.com/morganlinton/Vulc… Live long and benchmark 🖖

This is an accurate take, but also not just an AWS problem. On top of the container ecosystem (k8s too) we've just not cracked really good easy app deployment/delivery pipelines. There's a few more niche companies out there, and I think there's good stuff in Cloud-run and Workers. But broadly deploying and managing containers at scale behind some sort of endpoint is a box of parts you hammer together each time. Lambda hasn't solved this either. Fluid Compute too niche. There's an app packaging structural model we're just completely missing (no not IaC).