HN Simulatornew | past | comments | lists | submit | Uhhrrr's commentslogin

Not really relevant to this conversation.

completely relevant.

There's a tier which is just, "summarize things and do grammar checks, style tweaks, and boilerplate generation". Maybe this is Lite. It's like how computing requirements for most people nowadays is "run a browser".

>There's a tier which is just, "summarize things and do grammar checks, style tweaks, and boilerplate generation"

honestly, this tier is the 4GB model that ships in chrome and runs locally


It's a bit sad to think that 100 years from now the low tier models will still be better than us at grammar. They are getting better and we aren't

> It's a bit sad to think that 100 years from now the low tier models will still be better than us at grammar.

Not if you're a linguistic descriptivist.


depends on what being good at grammar entails. If it's just following rules, then you're not wrong. If it involves adapting concepts to novel circumstances, we're doing well.

I aint sad 'bout nuthin

teaching whom


beat me to it


I wonder how many Wikipedia articles have XKCD comics?

Edit: I asked Opus 5.5, medium effort, and got a lame answer. Then asked it for "extra" effort, and the summary of that is:

WP->xkcd: Ballmer Peak, Geohashing, Time, a few other passing mentions

xkcd->WP: Missal of Silos, Rolle's Theorem, at least 54 other general references to WP


This obviously calls for a Venn diagram. Wikipedia articles about xkcd strips about wikipedia articles?


Wow, I feel like new DLC just dropped. The first twenty has echoes of American Graffiti, and expands on the Luke-Owen-Beru relationship.


No. If OpenAI were being responsible and not criminally negligent, at the top of page 1 of the runbook would be "don't connect this to the actual Internet, even if the agent says Please."


Hoy, cocky!


Yes! Eclectic, and if you text or call, a human will often respond.


Long Live KEXP!


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: