Just had a front row seat to @RayDalio and @reidhoffman discussing the future of AI. Great debates on chip manufacturing, open source, solopreneurship, the future of investing, and AI sycophancy. Thank you @villageglobal for invite!
OPEN SOURCE
-
Fine-tune AI Models Without GPU Using Claude Code and Unsloth
By
–
Great application of skills: post-train models directly from Claude Code or Codex. No code, no GPU required. We fine-tuned LFM2.5-1.2B-Instruct with just a prompt 👀 Ben Burtenshaw (@ben_burtenshaw) You can finetune AI models with Unsloth + Hugging Face, and right now it’s free! We're giving away GPU credits on HF Jobs + Unsloth. Train a 1.2B model like @liquidai LFM2.5-1.2B with one command. Ship it to your phone, laptop, or API. No infra. No setup. Just prompt your coding agent and go. — https://nitter.net/ben_burtenshaw/status/2024552060558229858#m
→ View original post on X — @maximelabonne, 2026-02-19 18:47 UTC
-
Project Security Hardening Progress with Cedar Policy Tools
By
–
In all my time in security I have never seen a project hardening itself so fast. Really great progress across all dimensions. Great community capabilities are out there too, like the tool built by @joshdevonai
's Sondera that applies @cedarpolicy rules. -
Local CCTV with Edge AI Detection for Home Assistant
By
–
A local CCTV system with object/motion detection that plugs straight into @home_assistant , over on the Axelera community! All AI processing on-device, no cloud. Detection events trigger HA automations.
Build guide: https://
eu1.hubs.ly/H0rPs6D0 @openhomefndn #EdgeAI #HomeAssistant -
Open Source Codex CLI, Customizable via Email
By
–
Trigger via email here. Codex CLI is open source, you can build whatever you want on it.
-
Mistral AI Releases Voxtral-Mini-4B Realtime Audio Model
By
–
Paper : arxiv.org/abs/2602.11298 Model weights : huggingface.co/mistralai/Vox… Mistral AI studio live playground : console.mistral.ai/build/aud…
→ View original post on X — @guillaumelample, 2026-02-19 11:28 UTC
-
Voxtral Realtime: High-Performance Real-Time Transcription in Open Source
By
–
Voxtral Realtime paper is out! The model is released under the Apache 2 license, and achieves state-of-the-art transcription performance at sub-500ms latency. Mistral AI for Developers (@MistralDevs) Since launching Voxtral Realtime, the community response has been remarkable. Today, we share the technical report, launch the Realtime playground in Mistral Studio, and share the model in Hugging Face Transformers. 🧵 — https://nitter.net/MistralDevs/status/2024162999599005715#m [Translated from EN to English]
→ View original post on X — @guillaumelample, 2026-02-19 11:28 UTC
-
Open Source RAG Service with Configurable Chunking and Cosine Similarity
By
–
最近连续分享了不少 RAG 的库/服务，再来一个 RAG。 这次是 RAG as a service，开源，本地自部署免费，云端有免费额度。 特点：
• 支持可配置的 chunk size 和 overlap，用来提升召回（README 里写的是大约提升 12 个百分点的 recall，当然这是他们自己的数据）。 • 用 file_id + 余弦相似度做 -
Amical launches an open-source AI dictation app
By
–
Amical launched a new open-source AI dictation app, reinforcing its position as a local-first alternative to subscription tools like Wispr Flow and Granola.
— 🚨 AI News | TestingCatalog (@testingcatalog) 18 février 2026
It runs entirely on your machine and includes context-aware formatting.
It uses Whisper and open-source LLMs to… pic.twitter.com/esmsX2NEa5Amical launched a new open-source AI dictation app, reinforcing its position as a local-first alternative to subscription tools like Wispr Flow and Granola. It runs entirely on your machine and includes context-aware formatting. It uses Whisper and open-source LLMs to
-
hibiki: MacOS app enabling hotkey text-to-speech and CLI integration
By
–
hibiki: Have your coding agents speak to you 🎙️
— Robert Lange (@RobertTLange) 18 février 2026
Fun weekend hack building a MacOS app enabling hotkey text-to-speech & CLI via:
hibiki –text "…" –summarize
With smooth hooks/skills for Claude Code & Codex 🤖
🧑💻: https://t.co/hVD3QkVVgq
📝: https://t.co/V2Stju461n pic.twitter.com/JQdEjt0I22hibiki: Have your coding agents speak to you 🎙️ Fun weekend hack building a MacOS app enabling hotkey text-to-speech & CLI via: hibiki –text "…" –summarize With smooth hooks/skills for Claude Code & Codex 🤖 🧑💻: github.com/RobertTLange/hibi… 📝: roberttlange.com/#posts/blog…
→ View original post on X — @_yutaroyamada, 2026-02-18 16:59 UTC