The best Claude Code security audit prompt. Plug this into Claude Code, and watch security errors disappear in minutes. Scan for data vulnerabilities, exposed API keys, config. mistakes, and more. Everyone should be using this:

🚨 BREAKING: Someone just open-sourced a tool that optimizes your website for AI search engines. It’s called geo-seo-claude. It optimizes any website for AI search engines like ChatGPT, Perplexity, and Claude. → Runs full GEO audits with parallel subagents → Delivers

I tested GPT 5.4, it came in 2x Cheaper than Opus 4.6, but interestingly Sonnet 4.6 is still 2x cheaper than GPT 5.4 on the same edit request in cursor. Using SONNET for UI/UX and GPT 5.4 for hard back-end builds feels like the move, what are you using right now?

GPT 5.4 is so slow, painful to use compared to to Claude models. But it's good

What model do you use for vibe-coding right now?

GPT 5.4 is like a calm, composed, developer who slowly and carefully builds out every feature effectively. Claude Opus 4.6 is like a cracked 10x developer who tells you to shut up and gets it done his way, whether you like it or not lol

Announcing Personal Computer. Personal Computer is an always on, local merge with Perplexity Computer that works for you 24/7. It's personal, secure, and works across your files, apps, and sessions through a continuously running Mac mini.

ChatGPT 5.4 for back-end coding is awesome, but the second it touches any UI or UX connected it sucks. Wish there was a way you could have claude do front-end and GPT backend for any prompt request

x.com/i/article/2032…

The computational power in your iPhone’s CHARGER is more than what was used to land on the moon.

It's now easier to build a custom piece of software for your company than to use a SAAS. Crazy times

In a world where any digital software can be built with a single prompt, who can survive? The companies that have a large, dedicated user base. You could build twitter from scratch, but who would use it? Having a platform is going be more important than ever

New Anthropic research: Emotion concepts and their function in a large language model. All LLMs sometimes act like they have emotions. But why? We found internal representations of emotion concepts that can drive Claude’s behavior, sometimes in surprising ways.

He is Risen

when i visited the x palo alto office, i'd do early mornings because I was coming from EST timezone. at 6 am there was an XAI guy shaking back and forth in front of his keyboard with a toothbrush in his mouth. i think about him often these days