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

“Emergence” from LLMs is very similar to emergence from scaling transistors.

When you have only hundreds of them, you can barely add numbers. But the same fundamental technology scaled to millions, billions and then trillions, transistors can do things which will look magic to previous generations.


+1


Building a suite of libraries for basic stuff like webserver, sql integration, writing react components etc in Lean here https://github.com/orgs/theoriclabs/repositories?q=sort%3Ast...

> Can lean generate small static binaries the same way Go/Rust/C/C++ can?

Lean compiles to C and the binaries aren't huge, though haven't benchmarked this part yet.

> How practical is rewriting, say, grep in Lean?

Very, you should probably try it.


I belive we can do regular software much better using formal methods, and I want to better communicate the developing tools, learnings and methodology.

Would appreciate a quick reaction from the community.


Bummed, but I guess for me, doesn't mean cursor subscription ending though. Grok is a pretty amazing model for the speed and price on Cursor.


Does Grok have a subscription that competes with Claude Max $100 plan (genuinely curious)


Yes, any Cursor sub includes a separate tier of usage for Cursor/SpaceX first party models separate from usage of third party models.

I have a $20 Cursor sub still personally and would say that the usage for Grok models is much higher than what $20 gets you with Anthropic. I can't speak for the $100 plan but I would assume it scales similarly.

I rarely run out of my usage monthly even with the $20 plan.


I'm on the $20 plan too and the only time I run over is if I'm using Opus (or probably other third-party models). Grok and Composer seem nearly free at this point. Cursor also gave me a $100 credit for Grok after 81% of my usage was on TP models. I don't think Grok 4.6 is quite at the level of Opus 5, but it's close and so much faster (and less chatty).


It's a little confusing because Grok and Cursor kinda live in different worlds. Grok has SuperGrok and SuperGrok Heavy ($300 a month!)

The best bet is Cursor Ultra ($200), which is the equivalent a month plan that you get from OpenAI and Anthropic. I get a LOT more capacity out of it because I almost always use the "Auto" mode, which auto picks between Opus 5, GPT 5.6, Grok 4.6, and Composer 2.5.

I like Auto mode so much actually. I use it for my Cursor work account as well because it's about 10x faster than just using Opus 5 or GPT 5.6 and about 90% is good. I switch back to the bigger models if I get in trouble, but that's pretty rare.

Vibe coding requires some discipline. You need understand what it's trying to do. If you have a good mental model you can keep it out of trouble. If you don't, it doesn't matter how good the model is. You're gonna end up in a mess.


Yes it does. You can either subscribe to grok directly or cursor. You have many tiers and all of them have generous usage.

Grok is a workhorse, not the smartest yet, but produces good code and follows the plan. Grok 5, which has been training since beginnig of this year, will probably be a monster. (10T/6T Param model variants)


https://3quarksdaily.com/3quarksdaily/2014/03/boundaries-and... This is a beautiful article on the subject.

To prove that there are unnamable concepts, he uses cantor's diagonal argument. There are countably infinite names. Any subset of these names is a concept, which is same as the powerset of the set of names, and through cantor's diagonal argument, there are uncountably infinite concepts, most which are not namable.

Yes you can take a specific concept, and name it, but there are uncountably infinitely many, so even with infinite time, you cannot name them all.



i think there must be a scheme of naming that is uncountably infinite too.


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

Search: