[dead]
Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
731–740 of 817 posts
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#732Earlier quoted context omitted.
philosophical nit picking here, I would say value-aligned rather than moral-aligned.
> philosophical nit picking here, I would say value-aligned rather than moral-aligned. How is trying to distinguish morals from values not philosophical nit-picking? EDIT: The above question is dumb, because somehow my brain inserted something like “Getting beyond the …” to the beginning of the parent, which…yeah.
To be fair, he did admit it is philosophical nit-picking.
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#733Earlier quoted context omitted.
People here need to learn to chill out and use the API. The GPT API is not some locked down cage. Every so often it'll come back with complaints instead of doing what was asked, but that's really uncommon. Control over the system prompt and putting a bit of extra information around the requests in the user message can get you _so_ far. It feels like people are getting ready to build castles in their mind when they ju…
[flagged]
[flagged]
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#734Earlier quoted context omitted.
Wait so you’ve gotten GPT 4 to successfully write TipTap extensions for you? Are you using Copilot or the ChatGPT app?
Not only writing, extending and figuring out quite complicated usage based on the API documentation. I'll open source some of them in the near future. I'm using ChatGPT Plus with GPT-4, that gave the best results. Also worked via API key and custom prompts.
Have you tried Bing? I’m also building a TipTap based app so hearing this is quite eye opening, I didn’t think LLMs were up to doing this kind of specialised library usage. Got any examples you could share?
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#735Earlier quoted context omitted.
Not only writing, extending and figuring out quite complicated usage based on the API documentation. I'll open source some of them in the near future. I'm using ChatGPT Plus with GPT-4, that gave the best results. Also worked via API key and custom prompts.
Have you tried Bing? I’m also building a TipTap based app so hearing this is quite eye opening, I didn’t think LLMs were up to doing this kind of specialised library usage. Got any examples you could share?
If you mean Bard, it's not available in the EU so I can't.
Of course, this one is almost fully authored by GPT-4:
https://hastebin.com/share/juqogogari.typescript
We also made extensions for:
font-weight
font-size
font-family
tailwind-manage
With different use-cases, the most interesting one is tailwind manager, which manages classes for different usage.
Tiptap is excellent when building a headless site-builder.
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#736I used GPT for preparing for some interviews. I kid you not 3.5 the free version produced some of the best questions and answers. I made it to finals and decided not to pursue the opportunity. Recently I started to pay for ChatGPT which gave me the access to 4.0. I tried similar prompts that I Had used to generate info and questions for my interview with 4.0 and boy I agree 4.0 was a mess. I actually only use 3.5.
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#737OpenAI's models feel 100% nerfed to me at this point. I had it solving incredibly complex problems a few months ago (i.e. write a minimal PDF parser example), but today you will get scolded for asking such a complicated task of it. I think they programmed a classifier layer to detect certain coding tasks and shut it down with canned BS. I like to imagine certain billion/trillion-dollar mega corps had a back-room say…
I think it is about how Microsoft may not want cannibalize its own products such as copilot. I also imagine that in the future OpenAI would prevent the whole chat with your own data feature in the name of data safety but it would be because Microsoft would want to sell that feature as part of office suite.
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#738OpenAI's models feel 100% nerfed to me at this point. I had it solving incredibly complex problems a few months ago (i.e. write a minimal PDF parser example), but today you will get scolded for asking such a complicated task of it. I think they programmed a classifier layer to detect certain coding tasks and shut it down with canned BS. I like to imagine certain billion/trillion-dollar mega corps had a back-room say…
I think the only real path forward is for somebody to create an open source "unaligned" version of GPT. Any corporate controlled AI is going to be nerfed to prevent it from doing things that its corporate master considers to not be in the interests of the corporation. In addition, most large corporations these days are ideological institutions so the last thing they want is an AI that undermines public belief in thei…
So, say I run my own 100% uncensored model.
And now it's butting heads with me. Giving answers I don't need and opinions I abhor.
What do?
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#739Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#740Earlier quoted context omitted.
People here need to learn to chill out and use the API. The GPT API is not some locked down cage. Every so often it'll come back with complaints instead of doing what was asked, but that's really uncommon. Control over the system prompt and putting a bit of extra information around the requests in the user message can get you _so_ far. It feels like people are getting ready to build castles in their mind when they ju…
The API chat endpoint dramatically changes its responses every few weeks. You can spend hours crafting a prompt and then a week later the responses to that same prompt can become borderline useless. Writing against the ChatGPT API is like working against an API that breaks every other week with completely undocumented changes.
> The API chat endpoint dramatically changes its responses every few weeks. You can spend hours crafting a prompt and then a week later the responses to that same prompt can become borderline useless.
Welcome to statistical randomness?