[HN Gopher] ChatGPT 5 is slow and no better than 4
       ___________________________________________________________________
        
       ChatGPT 5 is slow and no better than 4
        
       Have general LLMs clearly peaked?
        
       Author : iwontberude
       Score  : 40 points
       Date   : 2025-08-09 17:35 UTC (5 hours ago)
        
       | iwontberude wrote:
       | This is intended to be a discussion thread speculating about why
       | ChatGPT 5 is so slow and why it seems to be no better than
       | previous versions.
        
       | labrador wrote:
       | GPT-5 is better as a conversational thinking partner than GPT-4o.
       | It's answers are more concise, focused and informative. The
       | conversation flows. GPT-5 feels more mature than GPT-4o with less
       | juvenile "glazing."
       | 
       | I can't speak to other uses such as coding, but as a sounding
       | board GPT-5 is better than GPT-4o, which was already pretty good.
       | GPT-5's personality has definitely shifted to a more professional
       | tone which I like.
       | 
       | I do understand why people are missing the more synchophant
       | persoanlity of GPT-4o, but I'm not one of them.
        
         | saulpw wrote:
         | That sounds 10% better, not 10x better. That's close enough to
         | 'peaked'.
        
           | labrador wrote:
           | Agreed. Sam Altman definitely over-hyped GPT-5. It's not so
           | much more capable that it deserves a major version number
           | bump.
        
             | 3836293648 wrote:
             | Surely a major version bump says more about the internals
             | than the capabilities
        
               | labrador wrote:
               | I see your point from a software engineering perspective
               | but unfortuately that's not how the public sees it. The
               | common perception is that we are making leaps towards
               | AGI. I never thought AGI was close so I'm not
               | disappointed, but a lot of people seem to be. On the
               | other hand, I've seen comments like "I guess my fears of
               | a destructive super-intelligence were over-blown."
        
             | kjkjadksj wrote:
             | People seem to make this exact comment on here at every gpt
             | release. I wonder what gpt we ought to actually be on?
             | 1.4.6?
        
               | labrador wrote:
               | In retrospect I would have named it as follows:
               | 
               | GPT-4 -> GPT-4 Home
               | 
               | GPT-5 -> GPT-4 Enterprise
               | 
               | Because my impression after using GPT-5 that it is
               | designed to satisfy the needs of Microsoft mainly.
               | Microsoft has no interest in making AI therapists or AI
               | companions, probably because of the legal liability.
               | Also, that's outside their core business.
        
               | coldtea wrote:
               | 3.something.
               | 
               | They make "this exact comment on here at every gpt
               | release" because every GPT release is touted as
               | revolutionary and it's increasinly a smaller bump.
        
             | torginus wrote:
             | I still think it's a solid achievement, but weirdly
             | positioned. It's their new-poverty spec model, available to
             | everyone, and is likely not too large.
             | 
             | It's decently good at coding, and math, beating current
             | SOTA of Opus 4.1 by a small margin, while being much
             | cheaper and faster to run, hinting at likely a much smaller
             | model.
             | 
             | However it's no better at trivia or writing emails or
             | essays, which is what regular people who use ChatGPT
             | through the website actually care about, making this launch
             | come off as awkward.
        
             | hoppp wrote:
             | They gonna release new models like apple releases iphones,
             | same stuff little tweaks and improvements.
        
           | al_borland wrote:
           | By definition, if something is still getting 10% better each
           | year it hasn't yet peaked. Not even close.
        
             | coldtea wrote:
             | Getting 10% better over this last year compared to, say,
             | 100% and 50% and 25% better the 4-5 years before?
             | 
             | I'd say that points to it being very close to peaked.
             | 
             | Nobody said anything about a steady 10% year-over-year
             | being the case forever...
        
       | mikert89 wrote:
       | Have you used the Pro version? Its incredible
        
       | binarymax wrote:
       | My primary use case for LLMs are running jobs at scale over an
       | API, and not chat. Yes it's very slow, and it is annoying.
       | Getting a response from GPT-5-mini for <Classify these 50 tokens
       | as true or false> takes 5 seconds, compared to GPT-4o which takes
       | about a second.
        
         | jscheel wrote:
         | Doing quite a bit of that as well, but I've held off moving
         | anything to gpt-5 yet. Guessing it's a capacity issue right
         | now.
        
         | hoppp wrote:
         | If its 5 seconds maybe you are better off renting a GPU server
         | and running the inference where the data is, without round
         | trips and you can use gpt-oss
        
         | beering wrote:
         | The 5 seconds delay is probably due to reasoning. Maybe try
         | setting it to minimal? If your use case isn't complex maybe
         | reasoning is overkill and gpt-4.1 would suffice.
        
       | darepublic wrote:
       | They took away o3 on plus for this :(
        
         | Buttons840 wrote:
         | o3 was surprisingly good at research. I once saw it spend 6
         | full minutes researching something before giving an answer, and
         | I wasn't using the "research" or "deep think" or whatever it's
         | called, o3 just decided on its own to do that much research.
        
       | gooodvibes wrote:
       | Not having the choice to use the old models is a horrible user
       | experience. Taking 4o away so soon was a crime.
       | 
       | I don't feel like I got anything new, I feel like something got
       | taken away.
        
         | hirvi74 wrote:
         | 4o and perhaps a few other of the older models are coming back.
         | Altman already stated so.
        
       | pseudo_meta wrote:
       | API is noticeably slower for me, sometimes up to 10x slower.
       | 
       | Upon some digging, it seems that part of the slowdown is due to
       | the gpt-5 models by default doing some reasoning (reasoning
       | effort "medium"), even for the nano or mini model. Setting the
       | reasoning effort to "minimal" improves the speed a lot.
       | 
       | However, to be able to set the reasoning effort you have to
       | switch to the new Response API, which wasn't a lot of work, but
       | more than just changing a URL.
        
       | hirvi74 wrote:
       | I'm noticing significant differences already.
       | 
       | Code seems to work on the first try more often for me too.
       | 
       | Perhaps my favorite change so far is the difference of verbosity.
       | Some of the responses I am receiving when asking trivial
       | questions are now are merely a handful of sentences instead of a
       | dissertation. However, dissertation mode comes back when
       | appropriate, which is also nice.
       | 
       | Edit: Slightly tangential, but I forgot to ask, do any of you all
       | have access to the $200/month plan? If so, how does that model
       | compare to GPT-5?
        
         | dyauspitr wrote:
         | It's the same model at the $200 price point.
        
       | al_borland wrote:
       | It feels slower, but if the quality is better, so one response
       | will do instead of multiple follow up questions, it's still
       | faster overall. It's also still orders of magnitude faster than
       | doing the research manually.
       | 
       | I'm reminded of that Louis CK joke about people being upset about
       | the WiFi not working on their airplane.
        
       ___________________________________________________________________
       (page generated 2025-08-09 23:01 UTC)