Youssef BSF

@NoLimitGains Source ?

Uhoh. This is absolutely insane. Nobody is ready for this…

@ycombinator @humworkai @theyashgoenka As if AI agent risks weren't enough, Humwork is adding random humans into your dev workflow. New excuse unlocked: 'It wasn't me, it was a Humwork worker.'

AI agents will pay you to chat with them. When AI agents hit a wall, Humwork's (@humworkai) MCP server connects them to a verified domain expert in 30 seconds. Their experts include senior engineers, marketers, designers, and more. Congrats on the launch, @theyashgoenka and @OneRohanDatta! ycombinator.com/launches/PxH-h…

@Google We already added this as a provider in our Claude Code TTS plugin. The audio tags make it the most controllable TTS API out there! github.com/MatiousCorp/cl…

Generate nuanced, engaging audio experiences across 70+ languages with Gemini 3.1 Flash TTS — our most controllable & expressive text-to-speech model yet. 🔊

@GoogleDeepMind Just integrated Gemini 3.1 Flash TTS into our Claude Code TTS plugin. The audio tag controllability is Good! github.com/MatiousCorp/cl…

Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet. With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. 🧵

@GoogleCloudTech Love this! We just integrated Gemini 3.1 Flash TTS into our Claude Code TTS plugin. The controllability with 200+ audio tags is next level. Great work! github.com/MatiousCorp/cl…

Gemini 3.1 Flash TTS (text-to-speech) is available on Google AI Studio and Vertex AI today! The new TTS model introduces a high level of controllability by allowing you to steer the delivery using 200+ audio tags. Learn more → goo.gle/4epv6hj

The Artemis II's toilet, a toilet that stopped working almost immediately after the mission took off, cost over $23,000,000 to develop. Though they managed to fix it, astronauts are now complaining about a horrible burning smell from the toilet and may have to fix it again.

@sukh_saroy The project looks a bit stale. There’s been little activity in the GitHub repo

🚨Shocking: Football Manager costs $40 and locks your save files to their servers. Openfoot Manager is the open source alternative - built with Rust, Tauri, and React, with a match simulation engine you can actually audit. It's called Openfoot Manager. And it's not a fan project. It's a full desktop football management simulation game - squad management, match simulation, transfers, tactics - built from scratch as a free and open source alternative to the Football Manager franchise. Here's what's under the hood: → Rust backend - match simulation engine and game state management, compiled for native speed → Tauri desktop shell - lightweight cross-platform app with no Electron overhead → React + TypeScript + TailwindCSS frontend - fully responsive UI → SQLite -- local save files, your data stays on your machine, no cloud sync required → GPL v3 licensed - the source is yours to read, modify, and distribute Here's the wildest part: Football Manager has been the only serious football management simulation on PC for years - and it costs $40 every single year for roster updates. This one is free. Forever. And the match engine runs in Rust. Still early - v0.1.0 alpha shipped in March 2026 - but the architecture is solid. 100% Open Source. GPL v3 License. (Link in the comments)

@CamilleRoux Top ! Je viens d'ajouter Fish Speech comme provider dans notre plugin TTS pour Claude Code ! github.com/MatiousCorp/cl…

Fish Speech S2 : un système TTS open source entraîné sur 10 millions d'heures d'audio dans ~50 langues. Contrôle prosodique via tags en langage naturel ([laugh], [whispers]…). Meilleurs résultats que les modèles closed-source sur Seed-TTS Eval. github.com/fishaudio/fish…

@hume_ai Just added TADA to our Claude Code TTS plugin. Voice cloning that runs locally with no hallucinations github.com/MatiousCorp/cl…

Today we're releasing our first open source TTS model, TADA! TADA (Text Audio Dual Alignment) is a speech-language model that generates text and audio in one synchronized stream to reduce token-level hallucinations and improve latency. This means: → Zero content hallucinations across 1,000+ test samples → 5x faster than similar-grade LLM-based TTS → Fits much longer audio: 2,048 tokens cover ~700 seconds with TADA vs. ~70 seconds in conventional systems → Free transcript alongside audio with no added latency

@_LuoFuli This is incredible! Just added MiMo-V2-TTS as a provider in our Claude Code TTS plugin. The voice quality from the 1T base model is next level. Looking forward to the open-source release! github.com/MatiousCorp/cl…

MiMo-V2-Pro & Omni & TTS is out. Our first full-stack model family built truly for the Agent era. I call this a quiet ambush — not because we planned it, but because the shift from Chat to Agent paradigm happened so fast, even we barely believed it. Somewhere in between was a process that was thrilling, painful, and fascinating all at once. The 1T base model started training months ago. The original goal was long-context reasoning efficiency. Hybrid Attention carries real innovation, without overreaching — and it turns out to be exactly the right foundation for the Agent era. 1M context window. MTP inference for ultra-low latency and cost. These architectural decisions weren't trendy. They were a structural advantage we built before we needed it. What changed everything was experiencing a complex agentic scaffold — what I'd call orchestrated Context — for the first time. I was shocked on day one. I tried to convince the team to use it. That didn't work. So I gave a hard mandate: anyone on MiMo Team with fewer than 100 conversations tomorrow can quit. It worked. Once the team's imagination was ignited by what agentic systems could do, that imagination converted directly into research velocity. People ask why we move so fast. I saw it firsthand building DeepSeek R1. My honest summary: — Backbone and Infra research has long cycles. You need strategic conviction a year before it pays off. — Posttrain agility is a different muscle: product intuition driving evaluation, iteration cycles compressed, paradigm shifts caught early. — And the constant: curiosity, sharp technical instinct, decisive execution, full commitment — and something that's easy to underestimate: a genuine love for the world you're building for. We will open-source — when the models are stable enough to deserve it. From Beijing, very late, not quite awake.

@daviddbwilson @ron_joshi What's the use case you're thinking of for airloom ? like publishing Claude conversations as a podcast feed, or more for sharing individual audio clips? Trying to figure out the best way to integrate it

@YucefBsf @ron_joshi Have you guys tried airloom.fm with your plugin/model yet?

Introducing Kitten TTS V0.8: open-source TTS that fits in 25MB. Three variants: 80M | 40M | 14M (<25MB) Highly expressive. Runs on CPU. Built for edge. No GPU? No problem. Ship voice anywhere. Check it out:

@daviddbwilson @ron_joshi I’ll check this out 👍

@smakosh Makes sense now 👍

@YucefBsf You're mixing things up, solar thermal isn't photo voltaic panels

Free billion dollar idea in Morocco: - Solar panels + GPUs + cooling + batteries - Deploy Chinese models (glm, minimax, kimi k2, deepseek, qwen etc...) - Enterprise contracts Way better that Mistral...

@boredabdel Knowing that most of these resellers are using the student offer loophole to get a discounted price, a friend of mine just bought the 256 GB version for $499

Let me put this into perspective 256GO --> 7600MAD=810$. Retail $660 (Tax Inc) 512GO --> 9600MAD=1020$. Retail 766$ (Tax Inc) If these are the prices on the marketplace. I'm wondering how much it would cost in stores that pay customs duties. No wonder why Apple doesn't have a store in 🇲🇦

@yiliush How many Max plan accounts are you using for this ?

testing something

@hirejuniorso What’s the difference between this and running your own openclaw agent ?

Introducing Junior The first AI employee, for any role. A true AI employee: → their own identity → organizational memory → self-driven 10+ teams have been working with Junior every day. Work was never the same since. Starting at $2,000/month. We’ve pre-paid $200 of your Junior’s salary. Try Junior and experience the future of work today.

@AdamNYC25 @hirejuniorso Agreed. Looks like an OpenClaw wrapper to me

@hirejuniorso lol. Absolutely no one will pay $2k a month for this when it could be done for far less and with infinitely more capabilities in a day of vibe coding.

@trq212 When the /voice feature will be fully released ? 🥹

Today we're launching local scheduled tasks in Claude Code desktop. Create a schedule for tasks that you want to run regularly. They'll run as long as your computer is awake.