New on our Frontier Red Team blog: using Claude to formally verify software at large scale.
Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).
With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.
Read our research in full here: https://t.co/zUyx8CjBEk
Top 10 Favorite Film Titles:
The Illiac Passion
Funeral Parade of Roses
Heroic Purgatory
We Won't Grow Old Together
Here and Elsewhere
Killer of Sheep
Love Massacre
Hovering Over the Water
Landscape Suicide
Colossal Youth
verification is the biggest bottleneck for coding agents right now according to @addyosmani.
we @warpdotdev have put a lot of thought into building a good computer-use tool for Warp Factories. every agents gets a computer to navigate the apps they built, take screenshots and https://t.co/JHC9VfIZ44
Add near real-time decisions to your workflow with the Decisions API, now generally available.
Build faster, more cost-efficient apps and agents that can classify text and images, evaluate inputs, and determine what happens next without generating a full model response.
The Framer MCP is here. Design, build, and update your site with AI tools like ChatGPT, Claude, Cursor, and Grok. Without giving up Framer’s flexibility, reliability, and control. https://t.co/yt43GiqLBu https://t.co/kQkdr9Vd0t
It's time to retire long-lived static credentials.
We surveyed 1,000+ SaaS vendors and found only 8.4% support secure auth. This is our call to action and how we're doing our part.
https://t.co/yhWnPYeoAX
Opus 5.5 is the best work estimator model i've ever used. This is calibration that is increasingly important as we delegate more and more work — don't tell me that it's going to take 2-3 working days (what a human would do) when for you, an enthusiastic, indefatigable, and embarrasingly parallelizable AGI, can get it done in 2-3 hours.
We’ve open sourced an agent plugin that helps secure systems against recent cybersecurity threats.
You can install them with any agent or use them in Devin today:
https://t.co/K4DJpkeDBo
This summer, we invited METR and Redwood Research to pilot an embedded evaluation of our internal monitoring system, providing deep access to our infrastructure over three weeks.
Their findings helped strengthen safeguards as we expanded the system and will help shape future research collaborations with METR and other third party evaluators.
Not all forests are equal, and now we can map the difference. 🌳
Meet Forest Typology (ForTy): a 10m map of natural, planted, and farmed forests to help identify deforestation and protect the forests that matter most. 🧵
This is a huge moment for LlamaIndex and an incredible milestone for our research team: introducing OCRia-1, our new document parsing model.
OCRia-1 pushes the Pareto frontier on accuracy, speed, and cost, delivering SOTA results across the most complex of tables, charts, and dense formatting.
You can try it out live in LlamaParse, and if you're looking to migrate / processing at scale, we’re offering volume discounts and up to $3,000 in credits to make the switch for the next 48 hours*!
https://t.co/rzaFHLfdwz
Characters come alive in Rive. You draw them, rig them, and give them a personality that reacts in real time.
The Rive CLI speeds up the setup work, from building scenes to testing states, so you can get to the fun part faster. The creativity is still all yours. https://t.co/V0UMnuX5fg
Qwen3.8-27B reportedly jumped from 82 to 381 tokens/sec on a single RTX 3090 with 24GB VRAM.
That’s a 4.6× increase without changing the GPU or the model.
The developer, TeksEdge, achieved this by optimizing the inference stack rather than upgrading the hardware.
Here’s how
Since the beta, we’ve added new capabilities to the Decisions API so you can now use:
• Native GPT-Live integration so voice apps can react as people speak.
• Prompt caching to help lower costs when reusing context.
• Native JSON inputs so you can pass structured app data directly.
• Images in individual question instructions so you can compare multiple images against a shared reference.
• Up to 400 questions per request so you can make twice as many decisions in a single call.
https://t.co/7LtPr2XjKW
💚 Site of the Day - Lenval Properties
THEFIRSTTHELAST®
Ivan Chopei — @chopei_iv
Maks Stepenko
⚙️ ScrollTrigger, SplitText, CustomEase
🛠️ @webflow
site → https://t.co/iYJNo82uoy
showcase → https://t.co/zGjV9MynPN https://t.co/7czbF0fzD9
Blackmagic Camera to Cloud Workflow Seminar! Join us on Wednesday 28 October at 15:00 SGT to learn how to log in and set up Blackmagic Cloud in both DaVinci Resolve and the Blackmagic Camera app, and follow your media from the camera to the edit. Learn more at https://t.co/M4cFe5uISo
Cognition CSO @alexstamos will be hosting a fireside chat on Navigating the Security Dark Age this coming Monday at 10:30AM PST.
Register here: https://t.co/GBLRERZ69U
We have several LangChain-led and community-led meetups coming up! RSVP and bring a friend!
🇩🇪 10/27 Munich
🇺🇸 10/29 Washington, DC
🇲🇽 10/29 Mexico City
🇦🇪 10/31 Dubai
🇨🇦 11/4 Toronto
🇺🇸 11/5 San Francisco
🇬🇧 11/12 London
🇺🇸 11/12 Boston
🇺🇸 11/18 Seattle
🇸🇪 11/25 Stockholm
🇩🇪 12/4 Hamburg
RSVP: https://t.co/sillsOrXfh
Next stop on the LangSmith Roadshow? Chicago!
Hear about the current state of agent development, and get ready for two hands-on workshops focused on Deep Agents and LangSmith Engine.
Interested in attending? RSVP today!
https://t.co/Zxiteh1QFS
We’re also offering significant credits and support for customers on a Devin Enterprise plan to remediate these changes. More information:
https://t.co/PS4Ib7ZNIg
🤯 Explore in detail how @AlreadyBnChewed combines CG, live action, and AI through iconic brand films, rebrand concepts, and product animation tests!
Dive into this next gen production workshop now! ➡️ https://t.co/8o2SRPJ3tb https://t.co/jDUQGJyUFk
Different forests can look identical from above, so ForTy tracks how they have changed over time. 🌲🛰️
Built on AlphaEarth Foundations, our foundational AI model for planetary data, ForTy reads years of satellite imagery across 1.7M sites to help governments, companies, conservation groups and scientists build deforestation-free supply chains.
Published in @ScientificData, the ForTy 2020 map and the 2017–2025 time series are freely available today on Google Earth Engine - helping organizations build deforestation-free supply chains and protect the natural forests that matter most.
Find out more → https://t.co/hGzBRD7h3k
📚 Contra Labs just released a report on AI adoption, based on more than 150,000 responses.
Get the full scoop on Motion Mondays ➡️ https://t.co/GqlCZ2QKv4 https://t.co/iPoaEf44ho
