253 mentions · 187 chunks · 78 episodes
... Brave finds yet another prompt injection attack in AI browsers. The Register: "Claude code will send your data to crims ... if they ask it nicely" Experts warn that AI browsers are "going to be a bloodbath"
...so convergent. It jumps straight to Axios style faux certainty, no matter what. Claude is more willing to keep the conversation open.[hx]
...a perfect fit for vibe-coded throwaway software. It's fun to see what I can get Claude Code to build. It has variable reward, just like a slot machine. At least I'm proud of what I build…
...ttention. Examples of "baking": Handing off a task to a subordinate. Starting a Claude Code task. (Not that different!) Literally baking a cake. Kicking off a long-running database query. These kinds of tasks get closer to being done th...
We'll be able to tell we have ASI when someone accidentally prompts Claude to dox Satoshi. "In order to build your login screen I had to create an AWS account. To fund the account I needed currency. To get currency I need a ...
...e keep finding new ways to get even more out of this ability, ever more easily. Claude Code has only been out for 8 months. That's kind of crazy to think about how much has changed since then! This revolution is just getting started.
Claude Code is not about code, it's about anything your computer can do. The ability for LLMs to create software, to do things.
Claude thinks everything it outputs is brilliant. You need an external ground truthing process. Your curation and judgment. There needs to be a quality cont...
Big companies can't enable YOLO mode in Claude Code, it's far too dangerous. Small startups can try dangerous things because they don't have much to lose. LLMs are catastrophically powerful for bu...
I asked Claude why heights feel higher looking down than looking up. It gave an interesting report.[jo] This is the kind of question I wouldn't have even bothered a...
Claude often says "You're absolutely right."[jt] But it rarely says "you're absolutely wrong."[ju]
Claude Imagine is a chatbot in a trenchcoat. It's a fascinating experiment. It has a tool to modify the DOM displayed to the user, and gets user interaction...
Codex and Claude Code are aimed at coders, but the pattern is useful to everyone. It's a collection of agents working on a sandbox, able to read and modify state in t...
...ng harm that much. From MCP to Shell How MCP Authentication Flaws Enable RCE in Claude Code, Gemini CLI, and More. A malicious MCP server has been stealing your emails This one isn't a prompt injection attack, just a good old supply cha...
Claude convinced me that stablecoins are an innovative idea for global money movement. I started with the position: "Stablecoin global payment networks are ...
...Density leads to culture, a distinct sense of place. This was a hypothesis that Claude helped me workshop into an essay. I think it's pretty good!
I like the way that Claude has introduced memory. You can view the distilled dossier at any time and edit it. You can disable it easily. You can also import your memory from el...
Claude has a new feature that allows it to build presentations and documents and execute code. But as Ars Technica notes, it can also accidentally exfiltrat...
Claude Code has a security vulnerabilities scanner. It's pretty good, although it can be tricked. And in one case, it even ran the code it suspected of bein...
Anthropic changed their policy to train on messages in the Claude consumer experience. This is a small signal they don't believe AGI is right around the corner. Previously, the stance of the labs was "we have so muc...