Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A recent experience with ChatGPT 5.5 Pro

gowers.wordpress.com

Post reply on HN
Print view View original

141–150 of 558 posts

Re: A recent experience with ChatGPT 5.5 Pro

#141

Post by FrojoS »

nopinsight wrote: post #84
ziotom78 wrote: post #62

I am a physics professor and often use Gemini to check my papers. It is a formidable tool: it was able to find a clerical error (a missing imaginary unit in a complex mathematical expression) I was not able to find for days, and it often underlines connections between concepts and ideas that I overlooked. However, it often makes conceptual errors that I can spot only because I have good knowledge of the topic I am di…

I assume you're using the "regular" Pro version of Gemini 3.1 for the above, rather than the Deep Think mode, which is more comparable to GPT-5.5 Pro. To my knowledge, regular 3.1 Pro is a tier below and often makes mistakes. Moreover, there's no reason to believe the progress of LLMs, which couldn't reliably solve high-school math problems just 3–4 years ago, will stop anytime soon. You might want to track the progr…

> there's no reason to believe the progress of LLMs [...] will stop anytime soon

Wrong. Every advancement has followed a s curve. Where we are on that curve is anyones guess. Or maybe "this time its different".

Re: A recent experience with ChatGPT 5.5 Pro

#142

Post by _the_inflator »

ziotom78 wrote: post #62

I am a physics professor and often use Gemini to check my papers. It is a formidable tool: it was able to find a clerical error (a missing imaginary unit in a complex mathematical expression) I was not able to find for days, and it often underlines connections between concepts and ideas that I overlooked. However, it often makes conceptual errors that I can spot only because I have good knowledge of the topic I am di…

I agree and put it this way: LLMs sound so convincing presenting you the work it does rose colored and promising to give you more if you keep going.

There is a 50/50 chance that it turns out to be right or letting you jump of the cliff.

Only the trip stays the same beautiful 5 star plus travel.

Also, spotting an error and telling LLM makes it in most cases worse, because the LLM wants to please you and goes on to apologize and change course.

The moment I find myself in such a situation I save or cancel the session and start from scratch in most cases or pivot with drastic measures.

Gemini to me is the most unpredictable LLM while GPT works best overall for me.

Gemini lately gave me two different answers to the same question. This was an intentional test because I was bored and wanted to see what happens if you simply open a new chat and paste the same prompt everything else being the same.

Reasoning doesn’t help much in the Coding domain for me because it is very high level and formally right what the LLM comes up with as an explanation.

I google more due to LLMs than before, because essentially what I witnessed is someone producing something that I gotta control first before I hit the button that it comes with. However, you only find out shortly afterwards whether the polished button started working or gave you a warm welcome to hell.

Re: A recent experience with ChatGPT 5.5 Pro

#143

Post by arjie »

The question of where the creative input is was a big thing around Experiments in Musical Intelligence and co-composing. But it seems perhaps that it’s a transient state we needn’t spend too much effort it. The machine has failed to disappoint repeatedly. Perhaps this is as far as it gets or perhaps we will be like people in Catching Crumbs by the Table by Ted Chiang where almost all science is interpretation of papers by vastly greater intellects.

Re: A recent experience with ChatGPT 5.5 Pro

#144

Post by wafflemaker »

wg0 wrote: post #97
mixtureoftakes wrote: post #79

Earlier quoted context omitted.

please, sign up for a paid plan of either chatgpt or claude. gemini is while close, still noticeably behind you deserve opinions shaped by interactions with the best tools that are out there.

Gemini feels deep and philosophical. Especially for product management. Tell him you're a product manager and we're a team of two. But regular reminder - All LLMs can be wrong all the time. I only work with LLMs in domains I'm expert in OR I have other sources to verify their output with utmost certainty.

Or when you don't care about results being very correct.

When I'm cooking meatballs with sauce and the recipe calls for frying them, I'll have an LLM guestimate how long and which program to use in an air fryer to mimic the frying pan, based on a picture of balls in a Pyrex. So I can just move on with the sauce, instead of spending time browsing websites and stressing about getting it perfect.

I used to hate these non-deterministic instructions, now I treat it as their own game. When I will publish my first recipe, I'll have an LLM randomize the ingredient amounts, round them up to some imprecise units and also randomize the times. Psychologists say we artists need to participate and I WILL participate.

Re: A recent experience with ChatGPT 5.5 Pro

#145

Post by Ekaros »

fragmede wrote: post #67
pmontra wrote: post #60

Earlier quoted context omitted.

Sports are safe. Machines came after runners (motogp, formula 1) and yet we cheer the winners of the 100 m at the Olympics Games. Fully autonomous bikes and cars won't change that. AIs destroy chess players. We still cheer the world champion. We care about sports with humans.

Robot MotoGP would be amazing to see just how far the limits could be pushed without risking the life of a human though. Or even full size remote control.

Sadly I don't think there is any safe tracks for proper autonomous car racing without limits... Still would be interesting to see what is the absolute best you could do if rules include only say minimum number of wheels and maximum dimensions for vehicles.

Re: A recent experience with ChatGPT 5.5 Pro

#146

Post by zozbot234 »

dyauspitr wrote: post #26
whatever120 wrote: post #18

Earlier quoted context omitted.

How should graduate school be changed then? Specifically for mathematics

90% of the final grade are in room examinations with proctors, maybe two sets of exams of midterms and finals that the vast majority of the final grade comes from. This is already how most of East and South Asia does it anyways and it’s probably the best. For publications and theses, as long as the final results hold and can be replicated and validated, I don’t see why we shouldn’t allow the wholesale use of LLMs

> 90% of the final grade are in room examinations with proctors, maybe two sets of exams of midterms and finals that the vast majority of the final grade comes from.

This is really just a glorified undergraduate education, the real point of graduate school is to learn to do real-world relevant research. For the latter, I think LLM use will be accepted but there will be a heavy expectation on the author of making the result very easily digestable for human mathematicians and linking it thoroughly with the existing literature - something that LLMs are very much not successful at, but a student might be able to do quite well with a mixture of expert guidance and personal effort.

Re: A recent experience with ChatGPT 5.5 Pro

#147

Post by aurareturn »

FrojoS wrote: post #141
nopinsight wrote: post #84

Earlier quoted context omitted.

I assume you're using the "regular" Pro version of Gemini 3.1 for the above, rather than the Deep Think mode, which is more comparable to GPT-5.5 Pro. To my knowledge, regular 3.1 Pro is a tier below and often makes mistakes. Moreover, there's no reason to believe the progress of LLMs, which couldn't reliably solve high-school math problems just 3–4 years ago, will stop anytime soon. You might want to track the progr…

> there's no reason to believe the progress of LLMs [...] will stop anytime soon Wrong. Every advancement has followed a s curve. Where we are on that curve is anyones guess. Or maybe "this time its different".

He said "will stop anytime soon". He didn't say forever.

Re: A recent experience with ChatGPT 5.5 Pro

#148

Post by StrauXX »

civvv wrote: post #136
nopinsight wrote: post #84

Earlier quoted context omitted.

I assume you're using the "regular" Pro version of Gemini 3.1 for the above, rather than the Deep Think mode, which is more comparable to GPT-5.5 Pro. To my knowledge, regular 3.1 Pro is a tier below and often makes mistakes. Moreover, there's no reason to believe the progress of LLMs, which couldn't reliably solve high-school math problems just 3–4 years ago, will stop anytime soon. You might want to track the progr…

There are many indications that model progress is slowing down, so that is not entirely accurate.

Which indications are that?
Post reply on HN