How to Design Its Own LLMs (2025)

But why would you want to be able to make it actually respect the instructions in there too.

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). "Those rethinks are load-bearing parts of your voice.”. Oops.

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. 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. Openai should figure out how to have LLM's help with your writing. "Rule Number One: You may not use a single word an LLM suggests to you." isn't helpful for probably the majority.

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.