How many times have you been to a hospital and thought, I could have fixed that myself if only I'd known how? With no equipment. In my case, never.

That article was way longer than I thought it would be.

https://en.wikipedia.org/wiki/Self-surgery

At least one time. Considering it's the only time I've been to the hospital for myself in the last 25 years, though, that's a lot! :)

A lot of the time they just send you home. Knowing that ahead of time would be phenomenally useful.

There's one here:

https://phys.org/news/2026-06-global-mycorrhizal-fungi-revea...

I've been using otvdm (aka winevdm) and it is very good. It works like the original ntvdm did when running on non-x86 platforms. It emulates the processor and translates 16-bit api calls into 32-bit api calls so things work as you'd expect.

https://github.com/otya128/winevdm

Is this the same Paul Graham who says that founders need to be the kind of people who are prepared to break the rules? That is, cheat.

His essays are, themselves, "cheating" (in the sense of a life hack). Say what people want to hear today, even if it contradicts what you said yesterday.

Same, and it is a shame. Reading it is wearisome.

No, because it's a trade secret. But you might not be in breach of copyright.

I suspect it's not possible (as an end user) to get a thinking trace from one of the models. But what happens with "thinking" is that the model has a conversation with itself in an attempt to home in on a better answer to the original prompt.

The "amount of thinking" is how long this internal conversation is allowed to progress. The longer it goes on the more it costs. It's all part of the token budget but, because this internal dialogue is hidden, it's not obvious to the end user.

> I suspect it's not possible (as an end user) to get a thinking trace from one of the models. But what happens with "thinking" is that the model has a conversation with itself in an attempt to home in on a better answer to the original prompt.

The model that summarizes what is inside the CoT/|thinking| tags is just an LLM, and it's just as jailbreakable/susceptible to prompt injection as any other LLM: https://x.com/lefthanddraft/status/1991076879877460322 (for those without X; that's Wyatt Walls demonstrating both getting the gemini summarizer to print the raw CoT, as well as just do random calculations, dump its system prompt, etc.)

I'm quite disappointed this wasn't about ear waggling.

It's copromancy. Picking through the clanker's doings in an attempt to predict the future.

Thanks, you taught me a new word today! https://en.wikipedia.org/wiki/Scatomancy

It feels like Greek mythology should have some metaphor for "apparently simple structure that is so complex it leads anybody that studies it into madness". But I can't think of any name to put there.

Maybe the idea of complexity is too modern.

Another option (he's using Windows) is "change what the power buttons do" in Control Panel to make the sleep button into a no-op.