ChatGPT just told me to put the turkey in my toaster oven legs facing the door, and you think it can replace school. Unless there is a massive architectural change that can be provably verified by third parties, this can never be. I’d hate for my unschooled surgeon to check an llm while I’m under.

Just curious, not being a turkey SME, what's the downside to positioning the turkey that way?

Most turkeys of my acquaintance would not fit into a toaster oven without some percussive assistance.

I see, I overlooked the 'toaster' part. That's a good world model benchmark question for models and a good reading comprehension question for humans. :-P

GPT 5.1 Pro made the same mistake ("Face the legs away from the door.") Claude Sonnet 4.5 agreed but added "Note: Most toaster ovens max out around 10-12 pounds for a whole turkey."

Gemini 3 acknowledged that toaster ovens are usually very compact and that the legs shouldn't be positioned where they will touch the glass door. When challenged, it hand-waved something to the effect of "Well, some toaster ovens are large countertop convection units that can hold up to a 12-pound turkey." When asked for a brand and model number of such an oven, it backtracked and admitted that no toaster oven would be large enough.

Changing the prompt to explicitly specify a 12-pound turkey yielded good answers ("A 12-pound turkey won't fit in a toaster oven - most max out at 4-6 pounds for poultry. Attempting this would be a fire hazard and result in dangerously uneven cooking," from Sonnet.)

So, progress, but not enough.

Don't worry, someone will put another hack on top the model to teach it to handle this specific case better. That will totally fix the problem, right? Right?

What's the alternate if someone didn't know something during a procedure? Just wing it? Getting another data point from an LLM seems beneficial to me.

Ask a human who does. If there are no competent humans on-call before the procedure starts, reschedule the procedure.

A trained professional making their best guess is far more capable and trustworthy than the slop LLMs put out. So yeah, winging it is a good alternative here.

Yeah, when I started I actually had no intention of doing a chat app, but it was a good way to learn how it works. Eventual goal with this is a sort of hybrid notes app. Not an llm bolted into Notes, either, but kind of a mix. Find myself using the llm app as a knowledge repo and it’s just not built for that. I’ll post a TestFlight link later if you want to try it out.

Thanks for checking it out. Thinking to do a more file/notes focused version esp on mac because it’s blazing fast there.

It’s inert, how bad could it be? /s

Commendable. I’m starting out on my second attempt at a learning app in my life, and I feel the same.

One of these is not like the other.

My money is on a larger iPad (think Microsoft Studio) that takes the place of an iMac. Likely 15” at first, larger later. I really enjoy a keyboard and trackpad with an iPad and an external monitor. This would be my only machine if I could run Xcode/Terminal on it.

Your point is true, but this “interview” is mostly nonsensical fearmongering with no substance.

There's some hyperbole in what Bezmenov claims will be the consequences, but psyops and information warfare are very much real, and have been in use for decades. If he defected from the USSR and worked as a propagandist, he would be very familiar with what these tools are capable of. And if you take a look at the current state of many Western countries, it aligns well with the effects of psyops. Whether it was done by internal or external forces doesn't matter much, but it would be naive to think enemies of the West aren't engaging in it, just as the West is[1].

[1]: https://www.washingtontimes.com/news/2022/sep/19/us-governme...

There's a very interesting read on the USMC University website that covers political warfare (which this would arguably fall into). Its freely available.