[dead]
GPT-5.4
731–740 of 868 posts
Re: GPT-5.4
#732the 1M context is cool but tbh the token cost problem nobody's talking about is tool schema bloat. before the model writes a single line of code it's already consumed thousands of tokens just ingesting function definitions. i've seen agent setups where 30-40% of the context window is tool descriptions before any actual work happens. the per-token price war is nice but if your schema is 10k tokens of boilerplate you'r…
1. everyone talks about this
2. have you seen GPT5.4 new ToolSearch functionality? thats suppose to handle exactly that.
Re: GPT-5.4
#733the 1M context is cool but tbh the token cost problem nobody's talking about is tool schema bloat. before the model writes a single line of code it's already consumed thousands of tokens just ingesting function definitions. i've seen agent setups where 30-40% of the context window is tool descriptions before any actual work happens. the per-token price war is nice but if your schema is 10k tokens of boilerplate you'r…
what do you mean nobody is talking about tool schema bloat. everybody is talking about it, and why it’s the general recommendation to just use CLI whenever possible.
Re: GPT-5.4
#734Earlier quoted context omitted.
It's not particularly about x.com, hundreds of site like x, youtube, facebook, linkedin, tiktok etc surreptitious add tracking parameters to their links. The iOS Messages app even hides these tracking parameters. I don't like being surreptitiously tracked online and judging by the success of my free app, there are millions of people like me.
so, since these companies have to comply with removing PII, is the worst thing that could happen to me, that I get ads that are more likely to be interesting to me? i’m not being facetious, honest question, especially considering ads are the only thing paying these people these days
Who has to comply with removing PII? Your profile, yours, mapped to a special snowflake ID, is packaged and sold across a network of 2500 - 4000 buyers, including in particular those that clean, tie (a surprisingly small footprint turns into its own "natural primary key"), qualify, and sell on to agencies. No step in this is illegal.
https://www.theverge.com/2024/10/23/24277679/atlas-privacy-b...
Re: GPT-5.4
#735So, are we way into diminishing returns for these models at this point? If so, I think we can calculate when it will be available at home. Given this requires a GB200 NVL72 which has about 1,440 PFLOPS, the current 5090 chip has about 1,676 TFLOPS, so about a 1000x scale-up to the GB200. If we can assume Moores law, which might be broken, but still. We are looking at log2(1000) = 9.96, or about 10 years.
Re: GPT-5.4
#736Earlier quoted context omitted.
I hit limit of Pro in about 30 minutes, 1 hour max. And only when I use a single session, and when I don't use it extensively, ie waits for my responses, and I read and really understand what it wants, what it does. That's still just 1-2 hours/5 hours. What do you do to avoid that?
You're probably having long sessions, i.e. repeated back-and-forth in one conversation. Also check if you pollute context with unneeded info. It can be a problem with large and/or not well structured codebases.
The last time I used pro, it was a brand new Python rest service with about 2000 lines generated, which was solely generated during the session. So how I say to Claude that use less context, when there was 0 at the beginning, just my prompt?
Re: GPT-5.4
#737Earlier quoted context omitted.
It's not particularly about x.com, hundreds of site like x, youtube, facebook, linkedin, tiktok etc surreptitious add tracking parameters to their links. The iOS Messages app even hides these tracking parameters. I don't like being surreptitiously tracked online and judging by the success of my free app, there are millions of people like me.
so, since these companies have to comply with removing PII, is the worst thing that could happen to me, that I get ads that are more likely to be interesting to me? i’m not being facetious, honest question, especially considering ads are the only thing paying these people these days
IMO the tracking, advertising, and attention market might just be societies biggest problem.
Certainly it employs a lot of people, as do cartels.
Re: GPT-5.4
#738I find it quite funny how this blog post has a big "Ask ChatGPT" box at the bottom. So you might think you could ask a question about the contents of the blog post, so you type the text "summarise this blog post". And it opens a new chat window with the link to the blog post followed by "summarise this blog post". Only to be told "I can't access external URLs directly, but if you can paste the relevant text or descri…
I had something similar happen with skills today. A popup appeared saying, "hey, did you know ChatGPT has skills?" Clicking on it opened a new chat window, and after some thinking it said, "I tried to launch the built-in skills demo flow, but it isn’t available". They barely test this stuff.
> They barely test this stuff.
In all fairness they are more focused on domestic surveillance these days.
Re: GPT-5.4
#739The marquee feature is obviously the 1M context window, compared to the ~200k other models support with maybe an extra cost for generations beyond >200k tokens. Per the pricing page, there is no additional cost for tokens beyond 200k: https://openai.com/api/pricing/ Also per pricing, GPT-5.4 ($2.50/M input, $15/M output) is much cheaper than Opus 4.6 ($5/M input, $25/M output) and Opus has a penalty for its beta >200…
Based on my experience with LLMs the larger your input context the bigger the chance of something going sideways in the response. Not sure how to address this properly.
Re: GPT-5.4
#740Earlier quoted context omitted.
[flagged]
Govt. contracts and terms allowing autonomous drone machines which can kill without any human in the loop have a very large difference I know the difference between this is none but to me, its that Anthropic stood for what it thought was right. It had drew a line even if it may have costed some money and literally have them announced as supply chain and see all the fallout from that in that particular relevant thread…
> I know the difference between this is none but to me
Edit: just a very minor nitpick of my own writing but I meant that "I know the difference between this could look very little to some, maybe none, but to me..." rather than "I know the difference between this is none but to me".
I was clearly writing this way too late at night haha.
My point sort of was/is that Anthropic drew a line at something and is taking massive losses of supply chain/risks and what not and this is the thing that I would support a company out of rather than say OpenAI.