
Azure MVP | vExpert NSX | VMware EUC Champion | Author | Speaker | AWS, Google | Blogger | Cloud Evangelist @SopraSteria_no
Brumunddal, Hedmark, Norge
Joined January 2012
- Tweets22.7K
- Following1.5K
- Followers4.6K
- Likes1.9K
Marius Sandbu retweeted
微软搞了个专门给 Claude Code、Codex 省钱的开源插件,实测成本降低 18.4%~30.9%。
项目叫 TokenEconomizer,不换模型,也不用修改 Agent 本身。
主要做三件事:
记住经验:同一个项目踩过的坑,下次不再重复
精简工具:自动移除长期不用的工具,减少 Token 消耗
打断死循环:发现 Agent 反复报错,提醒它换个思路
支持 Claude Code、Codex、Copilot CLI 和 Pi。
微软在 277 个 SWE-Bench 任务上测试,5 组模型配置全部降低了平均成本,其中 4 组任务成功率还有提升。
我觉得最实用的是打断死循环。AI 有时候一个 Bug 能反复折腾几十轮,Token 就这么烧没了。
你更希望 Agent 省 Token,还是宁愿多花点钱,确保任务一次做对?
github.com/microsoft/TokenEc…
#agent #ClaudeCode #Codex #AI #OpenSource
Privacy should advance as fast as intelligence. OpenAI Private Intelligence gives businesses stronger controls over their data while using our most capable models.
We’re building these protections in close collaboration with some of our largest customers to help businesses apply frontier AI to their most sensitive work.
openai.com/business/private-…
Marius Sandbu retweeted
We've raised the max request size for Messages and Token Counting on the Claude API from 32 MB to 128 MB.
Image-heavy requests like long computer-use sessions and big PDFs were previously hitting 32 MB with plenty of context window left. Now you get ~4x more room.
Marius Sandbu retweeted
Mistral Le Chonk can now run locally!
The 1 trillion parameter model runs on a Mac Studio with our 1-bit GGUF which retains 91% top-1 accuracy.
Le Chonk is the strongest Western open model to date.
GGUF: huggingface.co/unsloth/Mistr…
Guide: unsloth.ai/docs/models/mistr…
Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity.
💻 Built to build: Le Chonk ranks #1 on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis.
🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others.
Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it.
Read more from our team and customers 👇:
Marius Sandbu retweeted
Never forget Patrick Stewart delivering one of the most iconic Trek moments of all time. THERE ARE. FOUR. LIGHTS.
Marius Sandbu retweeted
Before enabling VS Code 1.144 agents, classify where they may run. Microsoft says Agent Host keeps sessions active locally or remotely; GitHub-hosted cloud sessions can continue while a developer computer is offline. Gain continuity without uncontrolled execution rerouting.
Marius Sandbu retweeted
Le Chonk model weights are out 🔥
Today, we release the weights of a new and improved Le Chonk, advancing the open frontier for agentic coding and cybersecurity.
💻 Built to build: Le Chonk ranks #1 on @cognition’s FrontierCode among open models, and sets a new benchmark for Pareto efficiency on @artificialanalysis.
🛡 Built to defend: State-of-the-art in cyberdefense, put through the paces by the world's leading cyber vendors, including @CrowdStrike, @cloudflare, @rubrik, @zscaler, and others.
Built for sovereignty: Make it yours. Download the weights on @huggingface , customize it with Mistral Forge, and deploy it wherever you need it.
Read more from our team and customers 👇:
Marius Sandbu retweeted
Very excited to share Genie 4, our incredible interactive world model, bringing together real-time physics, reasoning, and audio! Simulations within simulations, makes you wonder just how deep the rabbit hole goes... I have a feeling we will be finding out soon enough...
Marius Sandbu retweeted
I could watch this all day! Agent Radar might be the best way to show all of my agents running! (yes its animated too!)
Open GitHub Copilot app and start a new chat - "install and open this canvas - github.com/github/awesome-co…"
Amazing work from @awlnx
Marius Sandbu retweeted
MAI-Image keeps climbing!
MAI Image 2.7 Preview is now #3 on @arena's image editing leaderboard. #2 by lab and ahead of GPT-Image-2. That's a +45 point jump from 2.6.
Exciting news: MAI-Image-2.7-Preview from @MicrosoftAI just landed at #3 overall in the Image Edit Arena with 1470 pts! That puts Microsoft AI at #2 among labs.
This release is a +45 pt improvement from its previous variant, MAI-Image-2.6 at #7.
MAI-Image-2.7-Preview also improved across every category compared to 2.6:
- #3 in Product, Branding & Commercial Design (up from #8)
- #3 in Portraits (up from #9)
- #3 in Photorealistic & Cinematic Imagery (up from #6)
- #4 in Text Rendering (up from #11)
- #4 in Cartoon, Anime & Fantasy (up from #9)
- #5 in 3D Imaging & Modeling (up from #10)
Congrats to the @MicrosoftAI team on this release!
GPT-6.1 Terra continues to advance the cost-intelligence frontier across our model families.
It’s a significant step up over GPT‑5.6 Terra, with 50% lower standard API prices.
In ChatGPT Work and Codex, your usage allowance goes further with GPT‑6.1 Terra than with GPT‑5.6 Terra—and far more than with GPT‑6.1 Sol or GPT‑6 Astra.
For in-depth research or complex coding, choose GPT-6.1 Sol or GPT-6 Astra.
GPT-6.1 Terra: delivering fast and capable computer use at a lower price.
GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
🤖 Made with AI
Marius Sandbu retweeted
Congrats to @killa who solved stealmybitcoin.com hours ago but I screwed up which key went on the server (the flag was a root wallet WIF instead of the branch WIF).
Check out their awesome writeup here: github.com/KillaBoi/StealMyB…
Marius Sandbu retweeted
And we’re just getting started!! (It’s more fun than I thought too)——fun stuff and guests lined up for week 3 🥳
#SaveStargate
#AFullCirclePodcast
Replying to @MichaelShanks
This new channel is shaping up into something really special, much appreciate it Michael. Been fantastic.
Marius Sandbu retweeted
Microsoft open-sourced an app that watches you do a task once, then teaches your AI agent to do it for you. 4.3K stars.
How Skill Recorder works:
1. Hit record (⌘⇧R or Ctrl+Shift+R) and do the task normally. You can talk through it out loud too.
2. It captures your clicks, app switches, pages and terminal commands, all on your machine.
3. GitHub Copilot turns the recording into a list of steps you can edit.
4. One click turns it into a skill your agent can run, or an automation on a schedule.
It generalizes from one example, so recording yourself submitting one form teaches the agent to submit all of them.
Runs on Mac, Windows 11 and Ubuntu. Needs a GitHub account with Copilot access.
Install: copy the one-line command from the latest release:
github.com/microsoft/skill-r…
Live research with local models using the new Perplexity Portable Computer.
We are building a local-first, personalized AI news priority feed running on the Perplexity PPLX 27B.
Building new possibilities on AMD Ryzen AI Max+ architecture. bit.ly/4khjBvc
Marius Sandbu retweeted
TSK-1 is Taskade's intelligence layer. One prompt in, a working system out. 🧬
→ A CRM with pipeline and follow-ups
→ A client portal with approvals and status
→ An ops dashboard that stays live
It remembers, reasons, and runs. 19 seconds:
youtu.be/ZEgiGIWZMog


























