I posted a video last week introducing claude-trace and https://t.co/D0HNJLyict on my social media (xiaohongshu/douyin/wechat video), it went viral instantly, more 500k views and than 100K likes + bookmarks. However lots of audience report that claude-trace does not work on latest version of Claude Code because it went from npm installation to bun binaries so the monkey patch approach stop working. Wondering is there any plan to fix this? Really appreciate the work and I love claude-trace and cchistory. @badlogicgames
this OpenClaw bot finds restaurants with ugly menus, rebuilds them as live web menus, and mails the owner a postcard...on autopilot.
here's how agencies can land recurring contracts with this system:
- scrapes every restaurant in a city in real time
- filters by review count + rating + last menu update + photo quality
- pulls the real menu items from the official site, PDF, or Google reviews
- samples the brand palette from the restaurant's own visual identity
- renders a 9:16 brand-matched menu, hosted live at a QR-accessible URL
- writes a personalized postcard referencing a real reviewer and a real dish
- mails it to the registered office addressed to the owner by first name
every step from discovery to brand-matching to outreach is automated.
reply "MENU" + RT and i'll send you a free guide so you can build this too
Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found.
All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.
Wow. Incredible amount of SOTA training data now just available to China thanks to @mercor_ai leak. Every major lab. Billions and billions of value and a major national security issue.
I couldn't figure out why I never got /remote-control feature. Turns out I had CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 set months ago from some "must-have config" article. That flag also disables release notes and update notifications — so I was never prompted about new features.
If you set this flag and feel like you've been missing out, now you know why. The flag doesn't do exactly what it says, the "nonessential traffic" includes things probably essential to you.
Announcing a new Claude Code feature: Remote Control. It's rolling out now to Max users in research preview. Try it with /remote-control
Start local sessions from the terminal, then continue them from your phone. Take a walk, see the sun, walk your dog without losing your flow.
I am trying to intercept Claude Code network request to understand the underlying behavior, @sergeykarayev 's finding is awesome, he leveraged HTTP Toolkit to do MITM proxy and you can the actual system prompt and Claude Code Tool setup. super recommended
I wanted to better understand how Claude Code is wired under the hood, so I captured its API requests and pulled out the system prompt and tool definitions.
Also posting the full thing as a gist below if you want to dig in!
@petergyang We are using Claude Code and Codex, though pretty hard... Please let me know if need any help when you are in China. I use Claude Code daily and created lots of 100k+ view posts on xiaohongshu/douyin, something like: https://t.co/YP3epD3I9J
I posted a video last week introducing https://t.co/jn1T5ssWIS on my social media (xiaohongshu/douyin/wechat video), it went viral instantly, more 100k views and than 10K likes + bookmarks. The moment I made the video the github repo only 4.5k stars, now it has almost 10k, I am confident that probably because of my videos. Just want to say thanks for the great tool and sharing @jarrodwatts
Just did a full audit of my computer with Claude Code, with AI making supply chain poisoning worse, we desperately need a AI defense side solution. Andrei said he mostly vibe code little utilities himself, but that does not apply to everyone, wondering what better solution with economic incentives for someone to solve this?
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.
My video about Ghostty on xiaohongshu/douyin/wechat video just crossed 200k views with 10k+ likes, comments, and saves — honestly didn’t expect this level of response.
What surprised me most is how many people resonated with the feel of Ghostty, been using it alongside Claude Code and it’s become a core part of my workflow.
Huge shoutout to @mitchellh for building this — excited to see where it goes next 🚀
I posted a video last week introducing https://t.co/jn1T5ssWIS on my social media (xiaohongshu/douyin/wechat video), it went viral instantly, more 100k views and than 10K likes + bookmarks. The moment I made the video the github repo only 4.5k stars, now it has almost 10k, I am confident that probably because of my videos. Just want to say thanks for the great tool and sharing @jarrodwatts