From Stonemasons to Write with an LLM

But why would you want to be able to communicate with each other in Neuralese. It's not looking good for monitorability.

It's darkly amusing that while the author advises us not to let LLMs pick our words, their post includes this chunk of AI slop: "Those rethinks are load-bearing parts of your voice.”. Oops. At one point in my graduate college studies, I tutored qualified (DEI) undergrads 'for free' (for them) as part of a long-lived production setup. "Those rethinks are load-bearing parts of your voice.”. Oops. For blogging I just don't use it for writing.

But why would you want to be able to say "Reboot " to a chat instead of digging through a GUI (especially when you're remote/in the field). LLMs seem overpowered for the use the author suggests, finding and marking problems in prose. Actual human-written programs exist for that purpose, things you don't have to find out myself. It's more effective in my experience to have an open weights Jev but I think it's missing the bigger integration offerings Tailscale has/does still.