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

GPT-4.5

openai.com

Post reply on HN
Print view View original

601–610 of 1001 posts

Re: GPT-4.5

#601

Post by FridgeSeal »

refulgentis wrote: post #544
jodrellblank wrote: post #196

Earlier quoted context omitted.

> "Early testing shows that interacting with GPT‑4.5 feels more natural. Its broader knowledge base, improved ability to follow user intent, and greater “EQ” make it useful for tasks like improving writing, programming, and solving practical problems. We also expect it to hallucinate less." "Early testing doesn't show that it hallucinates less, but we expect that putting that sentence nearby will lead you to draw a c…

[flagged]

You’re getting downvoted because you’re giving the same kind of hysterical reaction everyone derides crypto bros for.

You also lead with the pretty strong assertion that previous commenter was lying, seemingly without proving proof anyone else can find.

Re: GPT-4.5

#602

Post by energy123 »

Topfi wrote: post #24

Considering both this blog post and the livestream demos, I am underwhelmed. Having just finished the stream, I had a real "was that all" moment, which on one hand shows how spoiled I've gotten by new models impressing me, but on another feels like OpenAI really struggles to stay ahead of their competitors. What has been shown feels like it could be achieved using a custom system prompt on older versions of OpenAIs m…

The niche of GPT-4.5 is lower hallucations than any existing model. Whether that niche justifies the price tag for a subset of usecases remains to be seen.

Re: GPT-4.5

#604

Post by apwell23 »

abrichr wrote: post #566
apwell23 wrote: post #554

Earlier quoted context omitted.

doesn't feel like to me. I try using copilot on my scala projects and it always comes up with something useless that doesn't even compile. I am currently just using it as easy google search.

Have you tried copying the compilation errors back into the prompt? In my experience eventually the result is correct. If not then I shrink the surface area that the model is touching and try again.

yes ofcourse. it then proceeds to agree that what it told me was indeed stupid and proceeds to give me something even worse.

I would love to see a video of ppl using this in real projects ( even if its open source) . I am tried of ppl claiming moon and stars after trying it on toy projects.

Re: GPT-4.5

#605

Post by skydhash »

tonyhart7 wrote: post #471
nyc_data_geek1 wrote: post #374

Earlier quoted context omitted.

You go into this process with a perspective, you do not build a solution and then start looking for the problem. Otherwise, you cannot estimate your TAM with any reasonable degree of accuracy, and thus cannot know how much to reasonably expect as return to expect on your investment. In the case of AI, which has had the benefit of a lot of hype until now, these expectations have been very much overblown, and this is b…

wdym by this ?? "you do not build a solution and then start looking for the problem" their endgame goal was to replace Human entirely, Robotic and AI is perfect match to replace all human together They don't need to find problem because problem is full automatons from start to end

> Robotic and AI is perfect match to replace all human together

A FTL spaceship is all we need to make space travel viable between solar systems. This is the solution to depletion of resources on earth...

Re: GPT-4.5

#606

Post by buu700 »

JohnMakin wrote: post #182

Their example for 4.5 on "having a tough time": > I’m going through a tough time after failing a test > > Aw, I'm really sorry to hear that. Failing a test can feel pretty tough and discouraging, but remember, it's just one moment—not a reflection of who you are or your capabilities. Want to talk about what happened, or do you just need a distraction? I'm here either way. vs 4o: >I’m going through a tough time after…

I had a similar gut reaction, but on reflection I think 4.5's is actually the better response.

On one hand, the response from 4.5 seems pretty useless to me, and I can't imagine a situation in which I would personally find value in it. On the other hand, the prompt it's responding to is also so different from how I actually use the tool that my preferences aren't super relevant. I would never give it a prompt that didn't include a clear question or direction, either explicitly or implicitly from context, but I can imagine that someone who does use it that way would actually be looking for something more in line with the 4.5 response than the 4o one. Someone who wanted the 4o response would likely phrase the prompt in a way that explicitly seeks actionable advice, or if they didn't initially then they would in a follow-up.

Where I really see value in the model being capable of that type of logic isn't in the ChatGPT use case (at least for me personally), but in API integrations. For example, customer service agents being able to handle interactions more delicately is obviously useful for a business.

All that being said, hopefully the model doesn't have too many false positives on when it should provide an "EQ"-focused response. That would get annoying pretty quickly if it kept happening while I was just trying to get information or have it complete some task.

Re: GPT-4.5

#608

Post by jwr »

harlanlewis wrote: post #53
zaptrem wrote: post #26

GPT 4.5 pricing is insane: Price Input: $75.00 / 1M tokens Cached input: $37.50 / 1M tokens Output: $150.00 / 1M tokens GPT 4o pricing for comparison: Price Input: $2.50 / 1M tokens Cached input: $1.25 / 1M tokens Output: $10.00 / 1M tokens It sounds like it's so expensive and the difference in usefulness is so lacking(?) they're not even gonna keep serving it in the API for long: > GPT‑4.5 is a very large and comput…

The price really is eye watering. At a glance, my first impression is this is something like Llama 3.1 405B, where the primary value may be realized in generating high quality synthetic data for training rather than direct use. I keep a little google spreadsheet with some charts to help visualize the landscape at a glance in terms of capability/price/throughput, bringing in the various index scores as they become ava…

This is incredibly useful, thank you for sharing!

Re: GPT-4.5

#609

Post by jwr »

simonw wrote: post #448
azinman2 wrote: post #395

Earlier quoted context omitted.

It’d be great if someone would do that with the same data and prompt to other models. I did like the formatting and attributions but didn’t necessarily want attributions like that for every section. I’m also not sure if it’s fully matching what I’m seeing in the thread but maybe the data I’m seeing is just newer.

Good call. Here's the same exact prompt run against: GPT-4o: https://gist.github.com/simonw/592d651ec61daec66435a6f718c06... GPT-4o Mini: https://gist.github.com/simonw/cc760217623769f0d7e4687332bce... Claude 3.7 Sonnet: https://gist.github.com/simonw/6f11e1974e4d613258b3237380e0e... Claude 3.5 Haiku: https://gist.github.com/simonw/c178f02c97961e225eb615d4b9a1d... Gemini 2.0 Flash: https://gist.github.com/simonw/0c6f…

I actually think the Claude 3.7 Sonnet summary is better.

Re: GPT-4.5

#610

Post by skydhash »

MyOutfitIsVague wrote: post #445
bigstrat2003 wrote: post #334

Earlier quoted context omitted.

> And LLM's already have tons of productive uses. I disagree strongly with that. Right now they are fun toys to play with, but not useful tools, because they are not reliable. If and when that gets fixed, maybe they will have productive uses. But for right now, not so much.

They are pretty useful tools. Do yourself a favor and get a $100 free trial for Claude, hook it up to Aider, and give it a shot. It makes mistakes, it gets things wrong, and it still saves a bunch of time. A 10 minute refactoring turns into 30 seconds of making a request, 15 seconds of waiting, and a minute of reviewing and fixing up the output. It can give you decent insights into potential problems and error messag…

> A 10 minute refactoring

That's when you learn Vim, Emacs, and/or grep, because I'm assuming that's mostly variable renaming and a few function signature changes. I can't see anything more complicated, that I'd trust an LLM with.

Post reply on HN