tarlow 🌱 retweeted
Today we’re launching Shield: AI-native defense against offensive agents.
Attacker agents probing your site? Don’t block them. Deceive them.
We pointed ARTEX — the autonomous AI pentester the FBI just warned about—at our own prod. 5 minutes in, it pulled /.env and /.git/config (200 OK) with credentials inside.
Shield turned ARTEX attack surface into a synthetic maze with fake endpoints, decoy credentials, and poisoned responses that hijacked its agent memory.👇
tarlow 🌱 retweeted
让 AI 边看视频边理解,门槛终于被一脚踹到了地板上!
Hugging Face 刚开源了目前全世界体积最小的视频多模态模型:SmolVLM2-256M
很多人以为给 AI 装上“眼睛”去读长视频,动不动要吞几十 GB 显存。这个仅有 256M(约 0.25B)参数的小家伙,直接把配置要求杀到了极限:
· 只要 1.38GB 显存:无论是轻薄本、手机端、树莓派还是几年前的老旧显卡,不到 1.5G 显存就能直接在本地完成视频推理!
· 专职“看视频”而非“生成视频”:吃进一段视频、一组连续帧或游戏屏幕录屏,它能实时用自然语言理解剧情、描述动作、做视觉问答(VQA)以及 OCR 文字提取。
· 跑分扎实的小钢炮:Video-MME 达到 33.7,MLVU 达 40.6,对于一个只有 256M 的模型来说,这理解能力相当凶悍。
· 开箱即用全免费:Apache 2.0 纯开源协议,GGUF 量化版也已经就绪,拉进 Ollama 或者 llama.cpp 就能单机离线跑。
拿来做实时游戏画面的屏幕助手、本地监控动作识别,或者挂在低算力边缘设备上,简直是神仙底座。
想在千元机或轻薄本上折腾“视频视觉 Agent”的兄弟,这个微型模型建议先存一份备用!
👉 模型地址与 GGUF 入口见评论区一楼
#AI #开源 #HuggingFace #大模型 #多模态
tarlow 🌱 retweeted
📢 Meet Qwen4-Max, your new AI teammate for work, creativity, and discovery!
Qwen4-Max is built on a new MoE architecture with native vision and a 1M-token context window.
Highlights:
- Outperforms Qwen3.8-Max with up to ~50% fewer tokens, while average cost per task drops over 60% in our internal evaluation.
- Advances real-world productivity through greater proficiency with professional tools, stronger long-horizon execution, and higher-quality deliverables.
- Handles real tasks, including 3D modeling, game development, manufacturing, finance, law, healthcare, and frontier scientific discovery.
- $1.5/M tokens for input, $4.5/M tokens for output, and $0.075/M tokens for implicit caching — all lower than Qwen3.8-Max, with implicit caching down by 70%.
The API is live on QwenCloud. You can also try Qwen4-Max on Qwen Studio, QwenWork and Qoder.
Start building today! 🚀
- Blog: qwen.ai/blog?id=qwen4-max
- API: qwencloud.com/models/qwen4-m…
- Token Plan: qwencloud.com/pricing/token-…
More to come! The open weights of smaller Qwen4 models will be released. Stay tuned. 👀
tarlow 🌱 retweeted
llama.cpp v1.0.0 is now available
huggingface.co/blog/ggml-org…
tarlow 🌱 retweeted
🚀 The full DeepSeek App experience, now via API
Search, files, links, safety, and voice. The capabilities behind the DeepSeek App are now available through the DeepSeek API.
Enable built-in features with a few parameters, or call standalone APIs such as OCR, ASR, and TTS. Build richer conversations or recreate the full DeepSeek App in your own application.
Try our open-source frontend demo, with support for importing DeepSeek conversation history.
🔗 Demo: cdn.deepseek.com/chat-demo
📦 Code: github.com/deepseek-ai/chat-…
📖 Details: api-docs.deepseek.com/guides…
1/4
tarlow 🌱 retweeted
Meet Gemini 4 Hydrogen: built for rapid coding, multimodal synthesis, and everyday workflows.
It finishes tasks 2.5x faster than 3.8 Flash and surpasses Argon on the @ArtificialAnlys Intelligence Index.
We're introducing the Gemini Decisions API in @GoogleAIStudio, powered by our new Gemini Decision 1 model.
Instead of generating a text response token by token, Gemini Decision 1 evaluates your input (across text, images, audio, video, and PDFs) against up to 1,000 questions to make fast, confident decisions in a single pass, with zero output tokens billed.
Here's a look at how it works 🧵
A vulnerability (worse_query) affecting iOS 26.7.1, 27.0.1, and 27.2 allows malicious apps to read local files from other apps, putting seed phrases, private keys, and login credentials at risk across the entire ecosystem. This is an iOS-level issue, not unique to Binance.
Immediate Action Required:
- Delete any apps installed from untrusted sources (such as sideloaded or manually signed IPAs).
- Update iOS and all apps to the latest official versions.
- If you suspect a breach, transfer funds to a new wallet created on a clean device and reset all active login sessions.
Never install unauthorized packages, and keep your software up to date.
Readers added context they thought people might want to know
Binance recommends updating iOS to the latest versions against worse_query, but researchers describe it as an unpatched 0day and Apple's iOS 27.2.1 notes omit any such fix.
github.com/forcequitOS/wo…
support.apple.com/en-us/149715
x.com/0xjohnny/statu…
tarlow 🌱 retweeted
my second hermes hackathon plugin submission.
stash - hermes plugin
A capture bin for your Hermes sidebar.
You see something - a post, a repo, a video, a screenshot, a half-thought - and you want it later without it living in your chat history. Paste it into Stash and leave. Come back whenever, or ask your agent to go through it.
Links, YouTube urls, image urls, uploaded images and plain text all go in the same box. Titles and thumbnails fill in on their own, fetched server-side, so nothing costs you a model call.
pushing the PR soon and creating the video.
tarlow 🌱 retweeted
My Nous Research Hermes hackathon submission.
Lazy Plugin. a lazy cat powered plugin creator UI.
A hermes desktop dashboard for creating plugins to contribute to the Hermes community. describe a plugin in a sentence, or start from your own hermes skills or cronjob you already have.
I wanted to create a UI where Hermes users can convert their ideas into plugins, or turn their existing workflows into plugins for the broader Hermes agent community - who knows what your doing everyday could be a contribution to the community.
Create, audit, edit and publish straight to github for merge review - all in a click of a button.
Everything made in house with Hermes Agent. Video created by Hermes, music by my own plugin hermes-band.
Video creation and direction is not my strong skillset, so the clunky video is what you get 😄
PR currently in review!
github.com/RegeneratusLabs/l…
🔥 MiniCPM Spark Program S2: Build What’s Next.
What would you build with MiniCPM to help an agent get things done? We’re inviting developers and researchers to share working projects, from useful tools and open-source integrations to agents that complete real tasks.
Choose your track:
• Open Build Track: Build applications, tools, hardware projects, or agent framework integrations with MiniCPM. Working examples and tutorials are welcome.
• On-Device Agent Challenge: Build agents that complete end-to-end tasks, with MiniCPM playing a meaningful role locally in understanding requests, selecting tools, or checking results.
Models for S2:
MiniCPM-OCR 1.0 / Jev · MiniCPM-V4.7 · A surprise MiniCPM model, coming soon 🎁
Using another MiniCPM model? Select the regular track in the submission form.
🏆 Rewards
Depending on the award level, selected projects can receive:
• Official showcase and promotion
• Inclusion in the MiniCPM developer case library
• Early access to new models and features
• Technical support and collaboration opportunities
• Exclusive MiniCPM gifts
🎁 Grand Prize
One Mac mini M6 for an outstanding project in the On-Device Agent Challenge. Full rules apply.
📅 Phase 1: Nov 2 – Dec 13, 2026
Building with MiniCPM? Share your work and join the Spark Program.
Submit your project: forms.gle/7AE8LrVEthPyRcQq5
tarlow 🌱 retweeted
Introducing Arete-27B: Qwen3.8-27B, post-trained to reinforce Western values.
Chinese open models are currently the strongest available, but they ship with state-aligned behavior in the weights. We built an 803-prompt eval across seven value categories, including freedom of expression, democracy, and privacy, and measured how often a model adopts China’s party line.
After fine-tuning on roughly 53 million tokens, Arete-27B's propaganda rate fell from 22% to 1%, in line with the Western models we tested. Its Hermes Bench score shows no significant performance tradeoffs.
The values in an open model are one fine-tune away.
Our eval, weights, and training data are available now along with the full blog post: nousresearch.com/arete
tarlow 🌱 retweeted
I spent 8 hours drawing GTA 6 in the sky but realistically I’ve been waiting 11 years for this moment. ✈️🎮 @rockstargames @grandtheftauto6
.
. @theflightdeckapp this looks absolutely amazing!!
.
. (Follow @thepilotpicasso for more sky art!!)
.
. #gta6 #grandtheftauto #aviation
tarlow 🌱 retweeted
materia release 1.0.0: blood panel in, cited supplement and herb options out.
every claim traceable to a source, withheld when the citation doesn't hold.
100% open weights on CPU: @OpenBMB MiniCPM5-2B for chat and reranking, MiniCPM-OCR-1.0 for lab-report OCR, llama.cpp, SQLite BM25, a deterministic safety screen.
Not a diagnosis, not a prescription. Local, no cloud, 100% private.
github.com/RegeneratusLabs/m…
tarlow 🌱 retweeted
Today we are rolling out Gemini Omni Flash 1.2, with:
- longer video generation (15 seconds)
- deeper cinematic controls for camera pov
- support for multi-turn conversation editing
- less visual drift
- 30% lower price than Omni Flash 1.1
Read more: blog.google/innovation-and-a…
Security release pre-alert:
We will release new versions of Node.js 22, 24, and 26 release lines on or shortly, after 2026-11-11 in order to address security vulnerabilities.
The highest severity issue fixed in this release is HIGH.
nodejs.org/en/blog/vulnerabi…
tarlow 🌱 retweeted
With the recent wave of vulnerability disclosures, it’s a good time to take a closer look at your own code.
Turn your coding agent into a team of security auditors with the open-source skill that seeded Cloudflare’s vulnerability discovery harness.
The 6 phase approach:
1. Map the codebase
2. Hunt for vulnerabilities
3. Challenge each candidate
4. Record the findings
5. Verify the findings
6. Report what’s confirmed, rejected, or still needs validation
Start your hunt here:
github.com/cloudflare/securi…



























