Claude Sonnet 3.5 – The New Benchmark in Conversational AI (bodt.io) 15 points by naveensky 2y ago ↗ HN
[–] [dead] naveensky 2y ago ↗ [flagged] [–] mansoor_ 2y ago ↗ These poorly prompted AI comments are lame [–] okasaki 2y ago ↗ I think that's part of the joke? [–] naveensky 2y ago ↗ in my defense, I thought I should summarise the article. I didn't realise it comes as first comment.My bad :(
[–] mansoor_ 2y ago ↗ These poorly prompted AI comments are lame [–] okasaki 2y ago ↗ I think that's part of the joke? [–] naveensky 2y ago ↗ in my defense, I thought I should summarise the article. I didn't realise it comes as first comment.My bad :(
[–] naveensky 2y ago ↗ in my defense, I thought I should summarise the article. I didn't realise it comes as first comment.My bad :(
[–] lobochrome 2y ago ↗ Getting it to enforce JSON is still a pain and not guaranteed. GPT-4o does this better.Also it’s vision capabilities are much less evolved. [–] naveensky 2y ago ↗ I agree with you, but I have been using Claude for programming for the last few days and I am impressed by difference in results [–] SwiftyBug 2y ago ↗ Not to mention that it is way less verbose than Chat GPT.
[–] naveensky 2y ago ↗ I agree with you, but I have been using Claude for programming for the last few days and I am impressed by difference in results [–] SwiftyBug 2y ago ↗ Not to mention that it is way less verbose than Chat GPT.
[–] atul_lakhotia 2y ago ↗ The results from Claude AI was lot better than ChatGPT. I had tried writing an ad copy for a client- Chatgpt gave very typical suggestions while Claude AI gave interesting different suggestions.
[–] opdahl 2y ago ↗ This reeks of AI generated blog spam created from a few other articles as input. [–] HermanMartinus 2y ago ↗ 100%
12 comments
[ 4.3 ms ] story [ 33.8 ms ] threadMy bad :(
Also it’s vision capabilities are much less evolved.