antirez@antirez
My second short story release in English is ready: Tales of Illustrious Computer Scientists: Iola Varga, nun and computer scientist.
2313261362K
antirez
@antirez
Reproducible bugs are candies. I like programming too much for not liking automatic programming. In elenco AGCOM.
806 Seguiti83.5K Follower43.9K Post
- antirez@antirezThanks to the new touch displays in modern laptops we can finally work slower and make more errors while working <3261849214.8K
- antirez@antirezantirezRT @MiniMax_AI: More reference control. Fewer denoising steps. More places to run H3. The latest community contributions span 8-step reference-conditioned video + audio, 4-step distillation, sparse attention, and reference-token compression - alongside serving and workflow integrations across GPU servers, TPUs, and Apple Silicon. What matters is what this enables: more affordable experimentation, finer creative control, and more choices about where and how video generation runs. Open models become more useful when the community can improve the methods, adapt the runtime, and build workflows around them. Credit to @haoailab @yisun0618 @lanfeng491270 @guocheng_qian @Alissonerdx @ddalcu @tazmannner @HaochengXiUCB @huggingface @Jhuaplin, and the PTD, DMAD, SparkH3, TorchTPU and FlashML teams - including Zhengming Yu and zechengtang on GitHub. 11 additions to the H3 ecosystem index. Thank you to everyone building, testing, and sharing.MiniMax (official) @MiniMax_AIOpen weights. Shared progress. MiniMax H3 is moving fast. We built H3 for video generation with native stereo audio and multimodal reference control. The open-source community is making that capability faster, more accessible, and easier to build on. Recent highlights: • FastH3 — FastVideo, Nuva Lab and NVIDIA: 4-step distillation, now running on DGX Spark and Apple Silicon. • Sol-H3 — NVIDIA’s SANA team: 15 seconds of 768p video + audio in 6.6 seconds on 8×B300, in the team’s warm-inference benchmark.* • VDN — Haocheng Xi and the OpenVDN team: rethinking attention for faster H3 inference, with weights, training and inference code released. • PDD — NVIDIA’s distillation method, brought to H3 by Alibaba PAI as 8-step Acc-LoRAs, now supported in ComfyUI. • LightX2V — 4- and 8-step Turbo LoRAs, with workflows for text, image and reference-conditioned video + audio. Behind every release are people training, optimizing, quantizing, testing and sharing. Special thanks to: @haoailab @nuvalab @NVIDIAAI @xieenze_jr @HaochengXiUCB @ArashVahdat @julberner @LightX2V @ComfyUI And to the individual contributors pushing the work forward: @haozhangml @cxlcl1 @lawrence_cjs @yitongli165665 @haopengl33 @songhan_mit @shanasaimoe Thank you for building with H3 and helping make it faster, more accessible, and more useful for the community. Powerful models go further when we build together. Keep pushing H3. Excited to see what comes next. 🚀 Explore the ecosystem:0430587
MiniMax (official)@MiniMax_AIOpen weights. Shared progress. MiniMax H3 is moving fast. We built H3 for video generation with native stereo audio and multimodal reference control. The open-source community is making that capability faster, more accessible, and easier to build on. Recent highlights: • FastH3 — FastVideo, Nuva Lab and NVIDIA: 4-step distillation, now running on DGX Spark and Apple Silicon. • Sol-H3 — NVIDIA’s SANA team: 15 seconds of 768p video + audio in 6.6 seconds on 8×B300, in the team’s warm-inference benchmark.* • VDN — Haocheng Xi and the OpenVDN team: rethinking attention for faster H3 inference, with weights, training and inference code released. • PDD — NVIDIA’s distillation method, brought to H3 by Alibaba PAI as 8-step Acc-LoRAs, now supported in ComfyUI. • LightX2V — 4- and 8-step Turbo LoRAs, with workflows for text, image and reference-conditioned video + audio. Behind every release are people training, optimizing, quantizing, testing and sharing. Special thanks to: @haoailab @nuvalab @NVIDIAAI @xieenze_jr @HaochengXiUCB @ArashVahdat @julberner @LightX2V @ComfyUI And to the individual contributors pushing the work forward: @haozhangml @cxlcl1 @lawrence_cjs @yitongli165665 @haopengl33 @songhan_mit @shanasaimoe Thank you for building with H3 and helping make it faster, more accessible, and more useful for the community. Powerful models go further when we build together. Keep pushing H3. Excited to see what comes next. 🚀 Explore the ecosystem:
8696937113K- antirez@antirezI believe StarTrek Voyager to be a masterpiece and often I think that, to make it happen, an incredible level of trust in a crazy project was needed (for StarTrek in general): people writing scripts and acting like all that crazy stuff mattered (they matter). It's not obvious.12313315.5K
- antirez@antirezDidn't know that. Will try.Marcos Saraiva @msaraivaf@kanwisher @antirez @OpenAIDevs CLI has it, "codex remote-control start" and it works way better than CC's.1208516K
Post @kanwisher@kanwisher @antirez @OpenAIDevs CLI has it, "codex remote-control start" and it works way better than CC's.401815.6K- antirez@antirezClaude /remote-control is becoming one reason to prefer Claude CLI versus Codex CLI sometimes, since it is too convenient. I'm not sure why @OpenAIDevs is lagging on that, many open issues and requests, and does not look too hard to add.119751275.8K
- antirez@antirezPost @antirezBtw sometimes I open a Claude session with /remote-control and ask it to open a tmux with Astra to do the work, and just report me from time to time and act as a proxy for my messages. This way I work in the tmux session when in front of the computer, and also control it remotely51599.9K
- antirez@antirezPost @antirezAnyway at this point there are little projects I do without using *both* Claude and GPT, one checking the work or the other, both collaborating on complex stuff and so forth.60478.6K
- antirez@antirezantirezRT @Kimi_Moonshot: 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 Work, Kimi Code, and the Kimi API. Open weights by Nov 4, 2026. 🔗 API: 🔗 Tech blog:03.2K0583
- antirez@antirezSupport coming for Strix / Gorgon Halo as well btw.antirez @antirezWork in progress, Iris.c in a DGX Spark running Flux 3 Klein. I know prompts for Flux 3 should be post-processed for better results, but it kind works even with humans written descriptions, more or less.03497.6K
- antirez@antirezThose products are not called "Claude Secretary" and alike in order to lower social anxiety?Claude @claudeaiWe’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.17820119.2K
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.2.4K4.3K55.5K11.2M- antirez@antirezantirezRT @jc50000000: Not #SLOPTOBERFEST but made on my LTX-MAC app native mac metal offline used minimax h3.c h/t @antirez010650
- antirez@antirezWhile Mistral Large 4 is a good news for Europe and AI, it is not a good fit for DwarfStar because of the very large number of active parameters, not just because of memory: would be too slow anyway. But anyway congrats to @MistralAI and waiting for a smaller MoE :D111337219.4K
- antirez@antirezComing from high end MacBooks the Dell XPS screen and colors are a shock. OLED is another world.438681187K
- antirez@antirezTrying @omarchy in a Dell XPS kindly donated by @dhh (I will try to adapt DwarfStar SSD streaming of large models btw, maybe it will be fast enough for QA usage). I'm really impressed by the "welcome" after the installation. The system is playful and not boring, which is cool.291662029.4K
