AI engineering, distilled. Agents, LLM systems, MLOps & infra architectures, papers, and tools worth your time.

Italy
Joined January 2016
Machine Learning FLX retweeted
10 GitHub repos to turn you into a design/motion studio. 550K+ stars total 1. impeccable (85K stars) Anti AI-slop design skill with 62 rule-based checks github.com/pbakaus/impeccabl… 2. UI UX Pro Max (139K) Generates a full design system (pattern, palette, type) from a project brief. github.com/nextlevelbuilder/… 3. MCP for Blender (32K) Connect Blender to any LLM. Prompt-driven modeling and scenes. github.com/ahujasid/blender-… 4. img2threejs (19K) Rebuilds the object in a reference image as code-only, animation-ready Three.js. github.com/img2threejs/img2t… 5. video-shotcraft (13K) Captures your real pages, picks from 150 shot recipes, renders a promo in Remotion. github.com/Vincentwei1021/vi… 6. HyperFrames (70K) Write HTML, render MP4, built for agents. Has a /figma skill that pulls brand tokens into video. github.com/heygen-com/hyperf… 7. Penpot (62K) Open-source Figma alternative with an MCP server, so agents can read your design files. github.com/penpot/penpot 8. Remotion (67K) Videos in React. The official skills repo teaches your agent how to use it. github.com/remotion-dev/remo… 9. lemo-opuscar (6K) 59 film styles made entirely in code, no video model. github.com/lemomo-ai/lemo-op… 10. diagram-design (60K) Agent skill that outputs diagrams as one HTML+SVG file, onboarded to your brand's colors and fonts. github.com/cathrynlavery/dia… Save this. Which one should I stress-test first?
47
97
10
1,103
74,795
Machine Learning FLX retweeted
New on our Frontier Red Team blog: using Claude to formally verify software at large scale. Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time). With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks. Read our research in full here: anthropic.com/research/forma…
612
1,022
588
9,437
1,886,760
Machine Learning FLX retweeted
We’re adding support for MCP Tasks and Elicitations in Claude. Tasks let Claude give plugins long-running jobs such as deep research and report back when they’re done.
253
275
141
5,264
474,322
Machine Learning FLX retweeted
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model. 🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal. 🔹 Full-project coding: games in Unreal, Unity & Godot. 🔹 Excels at parametric 3D modeling in Blender & CAD. 🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%. 🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks. Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API. Open weights by Nov 4, 2026. 🔗 API: platform.kimi.ai 🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
1,134
2,868
2,178
26,513
2,878,529
OpenAI used AI agents to test the security of its own training infrastructure. They found VM escape vulnerabilities, network misconfigurations and ways for isolated agents to communicate. The agents were explicitly instructed to look for vulnerabilities. The results show how difficult it is to isolate capable agents, even in environments designed for that purpose. openai.com/index/securing-ou…
1
1
438