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

GPT-5.2

openai.com

Post reply on HN
Print view View original

411–420 of 1001 posts

Re: GPT-5.2

#411

Post by jncfhnb »

chasd00 wrote: post #395
onraglanroad wrote: post #333

I suppose this is as good a place as any to mention this. I've now met two different devs who complained about the weird responses from their LLM of choice, and it turned out they were using a single session for everything. From recipes for the night, presents for the wife and then into programming issues the next day. Don't do that. The whole context is sent on queries to the LLM, so start a new chat for each topic.…

I was listening to a podcast about people becoming obsessed and "in love" with an LLM like ChatGPT. Spouses were interviewed describing how mentally damaging it is to their partner and how their marriage/relationship is seriously at risk because of it. I couldn't believe no one has told these people to just goto the LLM and reset the context, that reverts the LLM back to a complete stranger. Granted that would be pre…

It’s the majestic, corrupting glory of having a loyal cadre of empowering yes men normally only available to the rich and powerful, now available to the normies.

Re: GPT-5.2

#412

Post by n2d4 »

kingstnap wrote: post #225
preetamjinka wrote: post #72

It's actually more expensive than GPT-5.1. I've gotten used to prices going down with each latest model, but this time it's gone up. https://platform.openai.com/docs/pricing

Flagship models have rarely being cheaper, and especially not on release day. Only a few cases of this really. Notable exceptions are Deepseek 3.2 and Opus 4.5 and GPT 3.5 Turbo. The price drops usually are the form of flash and mini models being really cheap and fast. Like when we got o4 mini or 2.0 flash which was a particularly significant one.

That's not true.

    > Notable exceptions are Deepseek 3.2 and Opus 4.5 and GPT 3.5 Turbo.
And GPT-4o, GPT-4.1, and GPT-5. Almost every OpenAI release got cheaper on a per-input-token basis.

Re: GPT-5.2

#413

Post by brisket_bronson »

flkiwi wrote: post #401

I gave up my OpenAI subscription a few days ago in favor of Claude. My quality of life (and quality of results) has gone up substantially. Several of our tools at work have GPT-5x as their backend model, and it is incredible how frustrating they are to use, how predictable their AI-isms are, and how inconsistent their output is. OpenAI is going to have to do a lot more than an incremental update to convince me they h…

You are absolutely right!

Re: GPT-5.2

#414

Post by mmaunder »

onraglanroad wrote: post #333

I suppose this is as good a place as any to mention this. I've now met two different devs who complained about the weird responses from their LLM of choice, and it turned out they were using a single session for everything. From recipes for the night, presents for the wife and then into programming issues the next day. Don't do that. The whole context is sent on queries to the LLM, so start a new chat for each topic.…

Yeah I think a lot of us are taking knowing how LLMs work for granted. I did the fast.ai course a while back and then went off and played with VLLM and various LLMs optimizing execution, tweaking params etc. Then moved on and started being a user. But knowing how they work has been a game changer for my team and I. And context window is so obvious, but if you don't know what it is you're going to think AI sucks. Which now has me wondering: Is this why everyone thinks AI sucks? Maybe Simon Willison should write about this. Simon?

Re: GPT-5.2

#415

Post by block_dagger »

martinpw wrote: post #403
nullbound wrote: post #360

Earlier quoted context omitted.

I will say that it is wild, if not somewhat problematic that two users have such disparate views of seemingly the same product. I say that, but then I remember my own experience just from few days ago. I don't pay for gemini, but I have paid chatgpt sub. I tested both for the same product with seemingly same prompt and subbed chatgpt subjectively beat gemini in terms of scope, options and links with current decent de…

> I will say that it is wild, if not somewhat problematic that two users have such disparate views of seemingly the same product. This happens all the time on HN. Before opening this thread, I was expecting that the top comment would be 100% positive about the product or its competitor, and one of the top replies would be exactly the opposite, and sure enough... I don't know why it is. It's honestly a bit disappointi…

Replace "on HN" with "in the course of human events" and we may have a generally true statement ;)

Re: GPT-5.2

#416

Post by AstroBen »

simonw wrote: post #125

Wow, there's a lot going on with this pelican riding a bicycle: https://gist.github.com/simonw/c31d7afc95fe6b40506a9562b5e83...

Seems to be getting more aerodynamic. A clear sign of AI intelligence

Re: GPT-5.2

#417

Post by dwohnitmok »

MichaelZuo wrote: post #369
furyofantares wrote: post #319

Earlier quoted context omitted.

They also changed "roughly match" to "sometimes match".

Did they really change a meaningful word like that after publication without an edit note…?

This has definitely happened before with e.g. the o1 release. I will sometimes use the Wayback Machine to verify changes that have been made.

Re: GPT-5.2

#418

Post by didibus »

tenpoundhammer wrote: post #295

I have been using chatGPT a ton over the last months and paying the subscription. Used it for coding, news, stock analysis, daily problems, and a whatever I could think of. I decided to give Gemini a go when version three came out to great reviews. Gemini handles every single one of my uses cases much better and consistently gives better answers. This is especially true for situations were searching the web for curre…

> Overall, my conclusion is that ChatGPT has lost and won't catch up because of the search integration strength.

Depends, even though Gemini 3 is a bit better than GPT5.1, the quality of the ChatGPT apps themselves (mobile, web) have kept me a subscriber to it.

I think Google needs to not-google themselves into a poor app experience here, because the models are very close and will probably continue to just pass each other in lock step. So the overall product quality and UX will start to matter more.

Same reason I am sticking to Claude Code for coding.

Re: GPT-5.2

#419

Post by TechDebtDevin »

onraglanroad wrote: post #333

I suppose this is as good a place as any to mention this. I've now met two different devs who complained about the weird responses from their LLM of choice, and it turned out they were using a single session for everything. From recipes for the night, presents for the wife and then into programming issues the next day. Don't do that. The whole context is sent on queries to the LLM, so start a new chat for each topic.…

How are these devs employed or trusted with anything..

Re: GPT-5.2

#420

Post by twisterius »

mmaunder wrote: post #405

Weirdly, the blog announcement completely omits the actual new context window size which is 400,000: https://platform.openai.com/docs/models/gpt-5.2 Can I just say !!!!!!!! Hell yeah! Blog post indicates it's also much better at using the full context. Congrats OpenAI team. Huge day for you folks!! Started on Claude Code and like many of you, had that omg CC moment we all had. Then got greedy. Switched over to Codex…

[flagged]
Post reply on HN