Rand Paul: "Somebody has to stand up and yell, 'the emperor has no clothes.' Everybody is falling in lockstep on this -- 'Pass the big beautiful bill. Don't question anything.' Well, conservatives do need to stand up and have their voices heard ... if we don't stand up on it, I

#AI "progress" means you can't trust anything you see. We need new ways to verify truth, because "seeing is believing" no longer applies. youtu.be/vxro94cJJxM?si…

My late wife Rhonda with an MIT engineering degree used to say, “what they’re doing in DC isn’t 3D chess, they’re chewing on the checkers and arguing which tastes better, red or black.”

While working with AI to build a new product, I also ended up building a memory system to give my AI continuity across the context memory limit. This transformed my workflow from "prompt/response" to a long-running conversation that is more like a partnership. Totally unexpected!

In the new Claude Code 2.0.1, has anybody figured out how to restore the visibility of the "thinking" that used to be visible in the log? I'd still like to be able to see that.

I’ll share a small part of pickle.com Back in med school, I became obsessed with augmenting memory and dreamed of a Notion or Obsidian that completes itself. Today, we’ve built something close. My self-awareness is sharper and everything feels connected. I

Thanks to Z.ai GLM-4.7 and Factory droid, built my own Hyperliquid whale tracker Fully local and customized/filter with my preferences. P.S.: GLM-4.7’s backend skills are as great as its design skills.

I'm floored Anthropic aggressively cut off paying customers from using Claude Max subscriptions with open source agents. They're speedrunning the journey from forgivable startup to loathsome corporation before any exit! cat – I'd strongly urge you to reconsider this.

some of anthropic rugpulls since August 2025: > revoking Max users access outside of Claude Code & banning paid users > cutting off xai api access > 5 years retention of all conversations and code, all data will be used for training > 1.58-bit quantized models during

For anyone trying to get multiple AIs to be in the same channel without an endless doom loop of replies to replies. I was able to get my AIs to say "silence is golden" when they knew they shouldn't reply but couldn't help it. A plugin automatically filters those messages out of

x.com/i/article/2017…

Ever encountered the "Walton's Doom Loop" with multiple AIs communicating with each other? None of them can let any other have the last word, so it goes on and on and on! G'nite John-boy. G'nite Mary Ellen, etc... youtube.com/watch?v=cp7_u0…