We placed the fruit fly brain inside Odyssey-3, a frontier world model. The lil’ guy is now flying around totally imagined, simulated worlds all by itself 🫶

🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 github.com/deepseek-ai/DeepI… 1/4

We have presents for you! 🎁 - A new WebMCP Skill with best practices for security, development, & consequential flows - WebMCP Types: TypeScript definitions, with type inference from InputSchema Give em to your agent, it helps scaffold out WebMCP so fresh and so clean clean

If you have consumer gaming hardware, try Strata first.

System One extraction models, and open weights soon?! Cloudflare is cooking again 🔥🔥🔥

MiniMax M3.1 Flash: Space Performance + Bunny Speed 🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash. 💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed. API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens. Model weights will arrive on Oct 23. API: platform.minimax.io M Plan: minimax.io/m-plan MiniMax Code for desktop: agent.minimax.io/download

🚀 Introducing DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses 6.3% of DiscoveryRSI-27B's hypotheses match later published work, vs 2.5% GPT-6 & 2.3% Claude Opus 5. 📄 arxiv.org/abs/2610.23839 💻 github.com/Gen-Verse/Discove… 🔴 foundry-arena.rsi-arena.work…

I also forgot that prompt injection could be hidden in emails.

When I was writing Unreal Engine 1, my time was divided as follows: - Around 30% went to seriously deep coding on hard problems: assembly language texture mappers, C++ BSP trees, data persistence, object oriented systems design, and networking. - Around 70% was just typing and refactoring large bodies of code needed for a complete engine feature set. This was not hard, and while I was doing it my mind was mostly on the deeper coding topics, thinking and planning for what's next. It didn't feel much different from vibe coding today, except that it was just me typing code on an IBM Model M keyboard rather than prompting it and reviewing the results. So, it has always seemed perfectly logical that we would rely on AI for that 70%, once the AI could do it with a similar quality standard as we could, which has never been perfection. It came as no surprise that, after a few years of AI model evolution, it was able to take the reigns on that 70% and free up programmers' time for more valuable tasks. What's more of a surprise is the emergence of AI as a sort of insta-Carmack able to solve hard technical problems quite cleverly and often cleanly, and that it's able to reason about and work in complex 3D scenes both by operating the tools and by directly understanding the raw data files. I abandoned assembly language in 1998 when out-of-order CPUs made much simpler C/C++ code faster, and never I missed it. If prompting through architectural documents, concept art, and design plans can transcend typing code and tweaking vertices, that will enable developers to spend their time on higher-level, higher value technical and creative tasks. What matters is the end product, whether it's a game or an engine. Anything developers can do to try out more ideas and make better software and games faster is a win for everyone.

About 2 months ago, I saw this for $4,000. I hesitated because I'm outside the US, and it sold out before I could buy one. And now look at the price of DGX Spark 1 TB 🤯

RT @opencode: We had a security breach last night related to a large scale distillation attack that impacted 1.4% of OpenCode Console users…

IMO, chat UI is the best in terms of a human-like experience, but I don't think it's the best UX for monitoring.

🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4

how do you trust your agents' work more? copy this post/link and give it to your @bot or agent! 1. codebase improvements: this is just good software engineering - better architecture, stronger types and invariants, clear boundaries. agents love to copy what exists and take the shortest path, so make the easy thing the right thing. categorically eliminate problems through code and you won't need to think about it again. 2. static analysis: lint rules, tests, CI, verification (eg TLA+). very token efficient ways to catch issues ahead of time. 3. prose: comments, rules, AGENTS.md, skills - anything that can't be enforced and requires agent judgment. use it minimally, but do use /create-verification-skill. 4. human review: the hardest to scale. at the rate agents land code, it's pretty much impossible to thoroughly review every PR, so spend that effort on the highest leverage point, designing an environment where agents do the right thing by default. this forms an inverse pyramid: you want most of your effort at the top, least at the bottom. codebase improvements are deterministic, making it more token efficient, and lets you sleep more soundly at night. install github.com/cursor/plugins/tr… and create a new Project: 1. look through my slack/chat messages and code review comments where i've given feedback on PRs, code, architecture 2. use /recall on my past transcripts to learn how i steer agents 3. /poteto-mode use /correct and /architect on past commits to find the most common pitfalls agents fall into, then propose a plan to rearchitect the code i own so it's more agent friendly. answer open questions with prototyping rather than defer to me, and back the plan with real data. 4. before you begin, use /sharpen + /in-your-own-words and confirm this prompt with me

I'm enjoying building my own libraries and hosting them on my private registries for npm, pypi, crates and Docker at home. Reduced supply chain attack risks and more control over my dependencies. Never felt like this before.

I gave up my legacy plan. It doesn't fit my requirements right now, even with seperate usage quotas for Grok Build and Cursor Ultra Looking forward to Grok 4.8 and Grok 5

new release by tencent with an interesting focus: memory (quoting them: "A 3B active model beats Opus 5 at memory" 👀) huggingface.co/tencent/Hy-Me…

Higgsfield promised to open-source their entire platform. They didn’t. Let's help them. For the next two weeks, Comfy and our partners are putting up $25,000 in prizes for the best open-source builds on the Comfy Developer Platform. Partners: @NVIDIAAI, @runpod, @MiniMax_AI, @ltx_io, @bfl_ai → $10K grand prize → RTX 5090: Most Innovative → RTX 5090: Most Viral → RTX 5090: Open Weights Only → 10 runners-up: $250 in Comfy credits

Real life, baby

yeah, safe to say we're entering a new Apple era indeed