Claude 3.7 Sonnet and Claude Code

Post by milesrout » Tue, Feb 25, 2025, 11:44 AM UTC

LinXitoW wrote: post #283

hubraumhugo wrote: post #131

You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.

Got absolutely read to filth: > You've spent more time explaining why Go's error handling is bad than Go developers have spent actually handling errors. > Your relationship with programming languages is like a dating show - you keep finding flaws in all of them but can't commit to just one. > If error handling were a religion, you'd be its most zealous missionary, converting the unchecked one exception at a time.

Post by Pannoniae » Tue, Feb 25, 2025, 11:50 AM UTC

AlfeG wrote: post #729

Ahha, recently my daugher come to me with 3rd grade math problem. "Without rearranging the digits 1 2 3 4 5, insert mathematical operation signs and, if necessary, parentheses between them so that the resulting expression equals 40 and 80. The key is that you can combine digits (like 12+3/45) but you cannot change their order from the original sequence 1,2,3,4,5" Grok3, Claude, Deepseek, Qwen all failed to solve this…

Post by yarbas89 » Tue, Feb 25, 2025, 12:09 PM UTC

zaptrem wrote: post #783

mianos wrote: post #631

Earlier quoted context omitted.

I paid for it for a while, but I kept running out of usage limits right in the middle of work every day. I'd end up pasting the context into ChatGPT to continue. It was so frustrating, especially because I really liked it and used it a lot. It became such an anti-pattern that I stopped paying. Now, when people ask me which one to use, I always say I like Claude more than others, but I don’t recommend using it in a pr…

I have substantial usage via their API using LibreChat and have never run into rate limits. Why not just use that?

Post by sheepdestroyer » Tue, Feb 25, 2025, 12:30 PM UTC

s-macke wrote: post #766

akoboldfrying wrote: post #760

Earlier quoted context omitted.

The fact that the answer is interesting makes me suspect that it's not a good test for thinking. I remember reading the explanation for the answer somewhere on the internet years ago, and it's stayed with me ever since. It's interesting enough that it's probably been written about multiple times in multiple places. So I think it would probably stay with a transformer trained on large volumes of data from the internet…

Simple Bench goes in this direction: https://simple-bench.com/

Post by sarchertech » Tue, Feb 25, 2025, 12:37 PM UTC

jonplackett wrote: post #755

khafra wrote: post #698

Earlier quoted context omitted.

Yudkowsky just mentioned that even if LLM progress stopped right here, right now, there are enough fundamental economic changes to provide us a really weird decade. Even with no moat, if the labs are in any way placed to capture a little of the value they've created, they could make high multiples of their investors' money.

Yep totally agree. It will also depend who captures the most eyeballs. ChatGPT is already my default first place to check something, where it was Google for the previous 20+ years.