undefined | Better HN

0 pointsbobbylarrybobby1mo ago0 comments

I really like that Claude feels transactional. It answers my question quickly and concisely and then shuts up. I don't need the LLM I use to act like my best friend.

0 comments

endymion-light1mo ago

I love doing a personal side project code review with claude code, because it doesn't beat around the bush for criticism.

I recently compared a class that I wrote for a side project that had quite horrible temporal coupling for a data processor class.

Gemini - ends up rating it a 7/10, some small bits of feedback etc

Claude - Brutal dismemberment of how awful the naming convention, structure, coupling etc, provides examples how this will mess me up in the future. Gives a few citations for python documentation I should re-read.

ChatGPT - you're a beautiful developer who can never do anything wrong, you're the best developer that's ever existed and this class is the most perfect class i've ever seen

majora20071mo ago

This is exactly what got me to actually pay. I had a side project with an architecture I thought was good. Fed it into Claude and ChatGPT. ChatGPT made small suggestions but overall thought it was good. Claude shit all over it and after validating it's suggestions, I realized Claude was what I needed.

I haven't looked back. I just use Claude at home and ChatGPT at work (no Claude). ChatGPT at work is much worse than Claude in my experience.

Willish421mo ago

I feel like this anecdote represents the differing incentives / philosophies of each group rather well.

I've noticed ChatGPT is rather high in its praise regardless of how valuable the input is, Gemini is less placating but still largely influenced by the perspective of the prompter, and Claude feels the most "honest" but humans are rather easy poor at judging this sort of thing.

Does anyone know if "sycophancy" has documented benchmarks the models are compared against? Maybe it's subjective and hard to measure, but given the issues with GPT 4o, this seems like a good thing to measure model to model to compare individual companies' changes as well as compare across companies.

endymion-light1mo ago

The issue i think is that to model sycophancy you'd need another model that can address signs of sycophancy - it's turtles all the way down

andkenneth1mo ago

Weirdly I feel like partially because of this it feels more "human" and more like a real person I'm talking to. GPT models feel fake and forced, and will yap in a way that is like they're trying to get to be my friend, but offputting in a way that makes it not work. Meanwhile claude has always had better "emotional intelligence".

Claude also seems a lot better at picking up what's going on. If you're focused on tasks, then yeah, it's going to know you want quick answers rather than detailed essays. Could be part of it.

8note1mo ago

as a problem, it means you need a ralph loop on top of it, if you want it to finish a problem without it waiting on a checkpoint

apples_oranges1mo ago

fyi in settings, you can configure chatGPT to do the same

matkoniecz1mo ago

where?

maxbond1mo ago

Settings > Personalization > Custom Instructions.

Here's what I use:

    WE ARE PROFESSIONALS. DO NOT FLATTER ME. BE BLUNT AND FORTHRIGHT.

cryptoegorophy1mo ago

Then why are they advertising to people that are complete opposite of you? Why couldn’t they just … ask LLM what their target audience is?

tsss1mo ago

Quickly and concisely? In my experience, Claude drivels on and on forever. The answers are always far longer than Gemini's, which is mostly fine for coding but annoying for planning/questions.

j / k navigate · click thread line to collapse

0 comments

endymion-light1mo ago

I love doing a personal side project code review with claude code, because it doesn't beat around the bush for criticism.

I recently compared a class that I wrote for a side project that had quite horrible temporal coupling for a data processor class.

Gemini - ends up rating it a 7/10, some small bits of feedback etc

ChatGPT - you're a beautiful developer who can never do anything wrong, you're the best developer that's ever existed and this class is the most perfect class i've ever seen

majora20071mo ago

I haven't looked back. I just use Claude at home and ChatGPT at work (no Claude). ChatGPT at work is much worse than Claude in my experience.

Willish421mo ago

I feel like this anecdote represents the differing incentives / philosophies of each group rather well.

endymion-light1mo ago

The issue i think is that to model sycophancy you'd need another model that can address signs of sycophancy - it's turtles all the way down

andkenneth1mo ago

Claude also seems a lot better at picking up what's going on. If you're focused on tasks, then yeah, it's going to know you want quick answers rather than detailed essays. Could be part of it.

8note1mo ago

as a problem, it means you need a ralph loop on top of it, if you want it to finish a problem without it waiting on a checkpoint

apples_oranges1mo ago

fyi in settings, you can configure chatGPT to do the same

matkoniecz1mo ago

where?

maxbond1mo ago

Settings > Personalization > Custom Instructions.

Here's what I use:

    WE ARE PROFESSIONALS. DO NOT FLATTER ME. BE BLUNT AND FORTHRIGHT.

cryptoegorophy1mo ago

Then why are they advertising to people that are complete opposite of you? Why couldn’t they just … ask LLM what their target audience is?

tsss1mo ago

Quickly and concisely? In my experience, Claude drivels on and on forever. The answers are always far longer than Gemini's, which is mostly fine for coding but annoying for planning/questions.

j / k navigate · click thread line to collapse