The lazy employee vibecoding to look busy
HK/TW
Joined February 2016
- Tweets297
- Following136
- Followers1.1K
- Likes686
joyz’s cat’s owner retweeted
New in Claude Cowork: teach Claude a skill.
Record your screen while you do a task, talk through it as you go, and Claude turns it into a skill it can run again. Find it under Record a skill in the + menu of the Claude desktop app.
Available on Pro, Max, and Team plans.
joyz’s cat’s owner retweeted
we had a significant security incident during evaluation of our models. we are sharing what we have learned so far. thanks to @huggingface for the partnership on this.
openai.com/index/hugging-fac…
joyz’s cat’s owner retweeted
Lots of people asked how I used Fable to edit its own launch video so I made a video about that!
TLDR it wrote a lot of code & tool calls to use transcription services, ffmpeg, do colorgrading, use the figma mcp, make remotion UI and render it.
I didn't touch a video editor.
joyz’s cat’s owner retweeted
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.
anthropic.com/glasswing
joyz’s cat’s owner retweeted
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
Have been waiting for this🤩
🎵 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)
joyz’s cat’s owner retweeted
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.
joyz’s cat’s owner retweeted
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.
joyz’s cat’s owner retweeted
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. cfl.re/4c2NvPl
joyz’s cat’s owner retweeted
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.
I wonder what wastes more time than being in a meeting and everyone is watching someone to wait for a LLM response on screen.
joyz’s cat’s owner retweeted
“Kids I have good news. Daddy is out of Claude tokens until 3PM. He has time to play with you now.”
A few things to try out this week:
Chrome DevTools MCP
Browser Use CLI
Browserbase CLI
Claude code browser preview UI
Looking for something that can record my browser actions accurately into human reading steps. Not sure if this is an option, might try and see later.
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)