NAll news

All news

Saturday21 items

  1. Rohan PaulProduct release
    AI score62

    Elorian Releases Visual Reasoning Model Glimpse

    Elorian has released its first visual reasoning model, Glimpse, which is used to compare scene changes at different points in a video and to review the original clip when changes are subtle or rapid. Elorian calls this frame-based reasoning visual thinking. During reasoning, Glimpse can return to the source video, crop regions, extract specified frames, or run code to measure and compare what it sees; this mechanism is called visual scratch space. Co-founder Andrew M. Dai says it achieves frontier performance competitive with Astra on key public visual reasoning benchmarks.

    Quoted postAndrew M. Dai · @AndrewDai

    Spent years watching models ace a single image and completely whiff on anything that moves or changes angle. Today we’re fixing that. Try Glimpse now, our first visual thinking model with competitive frontier performance compared to Astra on key public visual reasoning benchmarks.

    Same story · 3 reports

    #Product updates#Video#Reasoning

  6. testingcatalogProduct release
    AI score63

    English translation is being prepared.

    Quoted postAIPOCH · @aipoch_ai

    Science, Open to All. We're building AIPOCH Open-Science for anyone with a question to explore. Research with AI, preserve the work behind each finding, and share a .science package for others to inspect, reproduce, and build on. Open-Science V 1.0.0 is alive! https://t.co/7R2sbiALrQ

    Same story · 4 reports

    #Product updates#Open-source ecosystem#Agents

  7. rohan_paulProduct release
    AI score62

    English translation is being prepared.

    Quoted postAIPOCH · @aipoch_ai

    Science, Open to All. We're building AIPOCH Open-Science for anyone with a question to explore. Research with AI, preserve the work behind each finding, and share a .science package for others to inspect, reproduce, and build on. Open-Science V 1.0.0 is alive! https://t.co/7R2sbiALrQ

    Same story · 4 reports

    #Product updates#Open-source ecosystem#Agents

  8. aravsrinivasProduct release
    AI score62

    English translation is being prepared.

    Quoted postComputer · @AskPerplexity

    REA (Reverse Engineer Anything) by @morluto is now a skill in Computer. Ask Computer to reverse-engineer an app and it inspects how the app works without its source code, then builds a working version. Tasks that use /reverse-engineer are free through October 31, up to 10,000 credits per user. Here are 5 apps Computer made with it, available to try for a limited time: 1) Figma: Design with layers and auto-layout, plus sign-in, cross-device sync, and multiplayer editing. Try it: https://t.co/FGGTblkCWY

    #Product updates#Agents#English text is being prepared.

  9. Jim FanProduct release
    AI score64

    Jim Fan's team open-sources the agentic robotics framework ASPIRE V1.0

    Jim Fan's team has open-sourced the agentic robotics framework ASPIRE V1.0, which features real-robot skill discovery and self-improvement capabilities. The team says that after switching backend models on the day Astra launched, all benchmarks reached about 99% overnight. In subsequent comparisons, Opus 5.5 slightly outperformed Astra on robotics simulation benchmarks, while Sonnet 5.5 landed on the Pareto frontier of cost versus robotics capability at $12 per task. ASPIRE and the /robot skill library were first launched in June.

    #English text is being prepared.#Embodied AI#Agents

Friday125 items

  3. shao_mengProduct release
    AI score71

    English translation is being prepared.

    Quoted postTencent Hy · @TencentHunyuan

    🚀 Hy Memory 2.0 is out — open-source model, framework, and MemHub. Your private memory steward. Framework handles chat, work & code memories. #1 open-source on 4 benchmarks. Hy-Memory-30B-A3B beats Opus 5 across major frameworks. MemHub (CLI + Mac) syncs across 10+ AI tools. 💻➡️ 🔗 SDK & MemHub: https://t.co/uP58VJanj8 🔗 Model: https://t.co/nTQbJ2q8dl #HyMemory #AgentMemory

    Same story · 3 reports

    #English text is being prepared.#Agents#English text is being prepared.

  4. shao_mengProduct release
    AI score71

    English translation is being prepared.

    Quoted postDenis Yarats · @denisyarats

    we open-sourced SPACE, the sandbox platform we use internally for secure agentic runtimes. it powers Computer as well as our RL training and evaluation workloads. https://t.co/W2XKKCnzgX

    Same story · 3 reports

    #English text is being prepared.#Agents#English text is being prepared.

  5. OpenRouterFirst-partyProduct release
    AI score55

    Krea 3 launches on OpenRouter with support for 1–4 reference images and native 2K editing

    Krea 3 is now live on OpenRouter. It is Krea AI's new image editing model, which accepts 1–4 reference images plus a prompt and returns natively 2K edited images, with most edits completing end-to-end in under 8 seconds. Pricing is $0.03 per 1K image and $0.06 per 2K image; reference images cost $0.02 per 1K image and $0.07 per 2K image. thinking_mode defaults to fast; when more prompt reasoning is needed, it can be set to high for an additional $0.02. The model uses the same Images API shared by other image models on OpenRouter, so migration only requires changing the model ID.

    Same story · 3 reports

    #Product updates#Image generation#OpenAI

  6. OpenRouterFirst-partyProduct release
    AI score55

    Krea 3 Image Editing Model Now Available on OpenRouter

    Krea 3 is now available on OpenRouter. This is Krea AI's new image editing model, which accepts 1 to 4 reference images and a prompt, and returns natively 2K edited images, with most edits completing end-to-end in under 8 seconds. Pricing is $0.03 per 1K image and $0.06 per 2K image; reference images cost $0.02 per 1K image and $0.07 per 2K image. thinking_mode defaults to fast; setting it to high adds $0.02. It uses the same Images API as other image models on OpenRouter, so migration only requires changing the model ID.

    Same story · 3 reports

    #Product updates#Image generation#English text is being prepared.

  7. OpenRouterFirst-partyProduct release
    AI score60

    Krea 3 Image Editing Model Launches on OpenRouter

    Krea 3 is now live on OpenRouter. This is Krea's new image editing model, which accepts 1 to 4 reference images plus a prompt and returns natively 2K edited images, with most edits completing end-to-end in under 8 seconds. Pricing is $0.03 per 1K image and $0.06 per 2K image; reference images cost $0.02 per 1K image and $0.07 per 2K image. thinking_mode defaults to fast; when more prompt reasoning is needed, it can be set to high for an additional $0.02. It shares the same Images API as other image models, so migration only requires changing the model ID.

    Same story · 3 reports

    #Product updates#Image generation#English text is being prepared.

  10. The New StackProduct release
    AI score65

    Cloudflare Open-Sources Void to Help IT Manage Employee Vibe-Coding Apps

    Cloudflare announced the open-sourcing of Void, which includes three components: Void SDK, Void CLI, and Void Platform. Enterprises can self-host the platform to deploy and manage apps built by employees with AI, and control who can deploy and access them. Void 1.0 is released together with the complete source code, and the SDK and CLI were previously published via npm under the MIT license. Self-hosting requires the paid Cloudflare Workers for Platforms plan, starting at $25 per month, plus R2 storage and a separately hosted PostgreSQL database; there is currently no fully managed version.

    #English text is being prepared.#English text is being prepared.#Open-source ecosystem