cloud agents just don’t seem to work for me
codex + mobile remote + disabling sleep on macbook lid close is peak
everyone talking about agentic payments for web requests, why wouldn’t model providers start acting like token banks?
trade token credits directly instead. if everyone is adopting LLMs, it might end up a valid form of payment.
stablecoins make sense too but more overhead
Alec Wantoch retweeted
So I have been testing the windows version of the codex app. No bluescreens so far which is nice.
Heads up, it does require your modem to be dialed up at all times. That's a bummer because I was expecting the AI stuff to be included with my local MSDN install.
everyone wants to automate the hard stuff
there's no such thing as "claude make me a billion dollars make no mistakes"
i just want to automate the boring easy/rote stuff that wastes time so i can get back to where my brain is actually useful
"LLM writes slop code unless you guide it properly"
"Oh let's just have LLMs review the code it produces"
Claude Opus 4.6 ~= creative full stack dev with design chops
GPT 5.4 ~= neckbeard backend & systems engineer
both very good or bad in different scenarios
funny how it feels like working with different teammates
the skill is deciding which to delegate to
So like…people actually believe moltbook is filled with agent-only convos, not just people larping as agents?
Alec Wantoch retweeted
Built this last night....... Claude Code Matrix Monitor hooks into Claude Code's native event system to visualize every tool call in real-time.
All of Claude's file reads, searches, edits, and bash commands stream via WebSocket to a cyberpunk dashboard that renders radar sweeps, pulse rings, code rain with actual code edits / diffs, and glitch effects.
It's project-local, non-invasive, and toggles on/off with one file. TLDR: you can watch the AI as it works....














