Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software.
It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans.
https://t.co/NQ7IfEtYk7
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
🎵 Lyria 3 and Lyria 3 Pro are now available in public preview via the Gemini API and in @GoogleAIStudio — and it’s music to our ears 🎵
🎼 Choose from two distinct variants to match production & latency needs (Lyria 3 Pro and Lyria 3 Clip)
📢 Direct the model with more precision & control (set specific tempos and song progression in your prompts)
🖼 Create projects using multimodal input support (such as image-to-music input)
if you're a performance marketer, here's how I use a custom Claude Cowork plugin to manage Google Ads at @AnthropicAI. it connects to the Google Ads API via MCP, encodes my common paid search workflows into skills, and works on desktop and Dispatch.
Software horror: litellm PyPI supply chain attack.
Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords.
LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm.
Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks.
Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages.
Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.
We’re introducing Dynamic Workers, which allow you to execute AI-generated code in secure, lightweight isolates. This approach is 100 times faster than traditional containers. https://t.co/c36Vkb7I0R
You can now enable Claude to use your computer to complete tasks.
It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk.
Research preview in Claude Cowork and Claude Code, macOS only.
@rezoundous I didn’t understand, until I have my lesson from the bad results. Not I’ve set myself some baseline to “glance” through the code in PR at least, say no hardcode, no secrets, no legacy or temporary keywords, no bad file naming, and no major bugs before merge.
Claude Code on desktop lets you select DOM elements directly, much easier than describing which component you want updated!
Claude gets the tag, classes, key styles, surrounding HTML, and a cropped screenshot. React apps also get the source file, component name and props
@vivoplt Have been working with one called Authgear for years. The team is very passionate and put a lot into designing the framework (I know them in person).
For any questions they’re also open to provide support. Pricing is also very generous, actually free to use for up to 2 projects.
Ended up instead of looping this back-and-forth until all things are setup, I learned a LOT of infra things through in the hard way, and he also figured out what we need to get it done by AI securely.
Maybe this is how IT coaching is like in this AI engineering gen (3/3)
Claiming myself as the “new gen AI vibecoder” type of product creator, my super senior technical CTO had a headache discussing with me on the infra and deployment flow lmao (1/3)
I kept throwing him AI responses and he needs to guess so hard why I was fallen into there. On the other hand, I couldn’t understand most of the responses from both of the AI Agent and my CTO. They talked very similarly with difficult words. (2/3)