Fer's

Part-time engineer, designer and developer. And... What's Next?

[Fer's @ferxalb]

I was so bored, so I made an OpenClaw Mini that was more secure, faster, and had excellent performance. 🙂

🔗: https://t.co/jGc8PmxRaA

#BuildingInPublic #OpenClaw

[Fer's @ferxalb]

@DotCSV Esto ya se veia venir, pero solo hay dos posibilidades: uno se quedaron sin computo por lo que apagaron el modelo a nivel mundial, o verdaderamente EE.UU. los bloqueo, personalmente apuesto por la segunda opción. Con el tiempo la verdad saldra a la luz.

[Fer's @ferxalb]

Minimax 3 is here! 🔥🔥🔥

[MiniMax (official) @MiniMax_AI]

Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities

- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- Natively Multimodal from Step Zero

API: https://t.co/fHRdSV7BwZ
Token Plan: https://t.co/BDCycxepZw
🚀New! MiniMax Code: https://t.co/GvB4YiB6Ul

Weights & Tech Report in ~10 Days

[Fer's @ferxalb]

@buildinpublic Making MaTE X turn AI coding agent work into evidence.

Every run gets identity, policy traceability, validation, Verified Task Score, signed evidence packs, and SOC 2 / procurement-ready exports.

Because “the agent fixed it” is not enough.

https://t.co/z9PtjXGWX1

[Fer's @ferxalb]

@ProductHunt Great, I'm ready to show you all what I've been working on in my spare time. 👀

[Fer's @ferxalb]

@buildinpublic Making MaTE X turn AI coding agent work into evidence.

Every run gets identity, policy traceability, validation, Verified Task Score, signed evidence packs, and SOC 2 / procurement-ready exports.

Because “the agent fixed it” is not enough.

https://t.co/z9PtjXGWX1

[Fer's @ferxalb]

@hthieblot MaTE X reviews real repos like a security-minded senior engineer: it finds risky changes, runs validation, and gives evidence-backed fixes before you ship.

[Fer's @ferxalb]

@hthieblot Pain is part of the process :)

[Fer's @ferxalb]

DeepSeek is back 🔥

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.

🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.

Try it now at https://t.co/GCdiMzk1Dl via Expert Mode / Instant Mode. API is updated & available today!

📄 Tech Report: https://t.co/drlDrxkYtp
🤗 Open Weights: https://t.co/T13Y8i7SDM

1/n

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.

🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.

Try it now at https://t.co/GCdiMzk1Dl via Expert Mode / Instant Mode. API is updated & available today!

📄 Tech Report: https://t.co/drlDrxkYtp
🤗 Open Weights: https://t.co/T13Y8i7SDM

1/n

[Fer's @ferxalb]

Base64 = 5.5. 👀

[OpenAI Developers @OpenAIDevs]

NS41

[Fer's @ferxalb]

@aarondfrancis Tauri is far too powerful, but if it weren't for WebKit... it would be the best. 😔

[Fer's @ferxalb]

It was worse than a 'hi' – the weekly quota dropped without me doing anything. I started a Codex session and, whilst I was typing, it dropped by 18%, and then it just kept draining away. I turned my Mac off, turned it back on, and it drained another 24% without me doing anything, lol. 😔

[Fer's @ferxalb]

@julesagent Jules Jules 🐙🔥

[OpenAI Developers @OpenAIDevs]

Introducing Euphony, an open-source tool for visualizing chat data and Codex session logs.

Paste in a public URL or upload a local file, and Euphony turns the raw data into an easy-to-browse view. It supports translation, filtering, editing, and more.

[Jerry Liu @jerryjliu0]

LiteParse is the best model-free, open-source document parser for AI agents.

It now gets a first-class landing page on our website 💫

Our company mission is building the world's best agentic document processing platform, and liteparse is the central pillar behind our OSS efforts. It's blazing fast (and getting faster soon!), supports 50+ file formats, and is one-shot installable as an agent skill.

Webpage: https://t.co/mVwma5QOCj

Come check it out: https://t.co/JNER0mVcB8

[Fer's @ferxalb]

@ErickSky @neogoose_btw Rust + Zig es una buena combinación bien interesante, pero necesitan integrarse perfectamente para funcionar de manera brutal.

[RyanLee @RyanLeeMiniMax]

This is my first time judging a hackathon at YC. This robot-themed hackathon is really creative

Michael is a 17-year-old high school student, but he won an award in this hackathon. Congratulations!

[Fer's @ferxalb]

Welcome Back Opus 4.6! 🤯

[Claude @claudeai]

Introducing Claude Opus 4.7, our most capable Opus model yet.

It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.

You can hand off your hardest work with less supervision.

[Miguel Ángel Durán @midudev]

¡Haz que tu IA deje de diseñar interfaces genéricas!

Han creado un repositorio con archivos DESIGN.md que replican la guía visual de grandes empresas.

Tienes de Apple, Airbnb, Tesla, Shopify, Uber y más...

Sin Figma. Sin JSON. Sin herramientas raras.

Copias el archivo en la raíz de tu proyecto y tu agente de IA entiende al instante cómo debe verse la interfaz.

Open source y gratis:
→ https://t.co/x6jKgy5Tst