Hacker Newsnew | past | comments | ask | show | jobs | submit | dankwizard's commentslogin

Good story mate but next time try and read the subject of the thread before you waffle on with your own blog post none of us subscribe to.

As a large language model, I did not write this comment

If you're wanting to actually improve over time, you'll have to drop a few. There's not enough time in the day to be a master of all trades. I'd suggest spending more time on Chess - Do a small learning component where you read a book or do some opening theory, then do a portion doing puzzles to learn tactics and spotting common positions in Chess games, then finally play some 10 minute games to put into action what you have practiced.

No thanks.

What an unaesthetic word. If you made it catchy, sure, but "subligence"? Try again


I would like to use Vivaldi but from my understanding they harvest just as much user data as Chrome. I'll stick to Brave for now.


Agree. The author of that article took 0 responsbility and despite the warnings of "Hey, AI with power in prod is a bad idea" thought "This wouldn't happen to me!" and then when it does "HOW COULD IT DO THIS?!"


Wouldn't be a thread about the tech that is changing the landscape for businesses across nearly every discipline without a pelican svg.


Dunning-Kruger vibes from this blog post.

Look into how LLMs work and it's pretty clear why these character counting scenarios often fail if not invoking Thinking/Python Scripting.


Hey, just woke up. Good morning, From my understanding, the reason that this happens is that as LLM's work from token to token which breaks the word being the reason why this type of anamoly occurs. The only thing I know is that I know nothing to be honest and I wish to learn more, and this was just me sharing something that I found interesting :-D

The thing which I find interesting though is that even if you don't involve Thinking, the r's in strawberry test always succeeds

https://chatgpt.com/s/t_69f85fb01d8881918016f2ceb3d1f314 & https://chatgpt.com/c/69f85e1d-25e8-8320-ba10-2dbe5857fc74

https://chatgpt.com/share/69f85fd6-4534-8322-a3f9-a06f3e26ec...

Now one can say that this patch was added as the r in strawberry got added into training test but I remember some comments at that time where it suddenly changed the answers as it started getting more humiliating for OpenAI as everyone started to pick this knowledge up and this might be the same reason why it says that it has three e's so many times because it tries to always say the three r's BUT that is just my opinion (which I don't wish to present as fact)

I think that the issue I have is that the people working in AI also present it sometimes as the holy grail when it has some clear flaws and they gloss over it.

If you found this result unsurprising, good for you!, but I feel like even as someone who spent a lot of time in the internet with LLM's, I didn't expect it because I thought that it was a completely solved problem in all LLM's, and I just shared this with everyone.

Have a nice day :-D


Really well written, technical post. Good read.


Thanks mkw5053


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

Search: