It burned out from too much stress, it probably needs a career break now to travel and some therapy.
Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
141–150 of 817 posts
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#142Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#143Earlier quoted context omitted.
What law prohibits Google from making Bard available outside the USA?
It's blocked in the EU because they don't want to/can't comply with GDPR.
Which is interesting, because if they can't comply within the EU, then how do they comply outside of the EU. With that I mean, if they have concerns that there is private data of EU citizens somewhere in that, then that is also in there for users outside of the EU. That said, they do not comply with GDPR anyway. If that its not the case, then they could also enable it for users within the EU.
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#144It's not just you. Probably they added some sort of classifier at the beginning to understand whether they should send it to 3.5 or 4. In my (very opinionated, undocumented, and mostly unscientific) opinion, more complex queries generally hit the old model, with the slow chugging of tokens. For example, I just asked it to refactor a very horrible POC in python that was creeping into the 200 LoC and it did the job wonderful. The prompt was:
`Can you refactor this function to make it: * More readable * Split on different parts * Easy to test
Consider the use of generators and other strategies. (code here)`
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#145Yes and I have to say I am using it less than I used to.
My gut feeling is they have to be careful now and don’t slack, because I have been using generative AI for a while now and I am not seeing the major problems being tackled. I also see a distinct lack of novel problems being solved. It’s just one website and/or marketing copy generator after another.
AI is awesome, but I am kind of on the fence if this generation is going to be actually useful.
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#146Just use GPT-4 via api?
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#147I noticed an apparent shift recently (for the worse) using Bing in creative mode, which is also supposed to be GPT4. Shorter answers, much more work to get it to output code, and maybe more bugs in the code it does produce...
It's funny, I really did feel like I'd lost something when I noticed it!
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#148Let me guess: the "woke fine-tuning" deteriorates quality of the model. Seriously, this lecturing style of GPT is totally useless. You ask it something vaguely unwoke, it lectures you about your style, you explain what it didn't understand about your request, it appologizes and does vaguely what you originally requested. This sort of deture is totally useless and a waste of my time. To stay with the terminology, if I…
Genuinely asking, what's an "unwoke" prompt?
Pretty sure framing it as unwoke is an overly specific issue, the problem stems from attempting to deal with malinformation as if it were fake news. Its no wonder that results turn shit once you start messing with the underlying reality model.
Its an especially bad idea as there are some actual safety risks when it comes to dangerous tutorials. Which will be costly to address. Political overhead is not something anyone can afford. Might be that if your proposed worldview depends on "properly educating" people, you might need to get used to the idea that you are adhering to a legacy system.
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#149It definitely seems to be getting worse with Clojure.
I tried some stuff yesterday, and it was making pretty rookie mistakes (misaligning parentheses, using `recur` in the middle of the function instead of the tail). It also was decidedly bad at catching my mistakes when I pasted code.
I sadly don't have a recording of this but I feel like a month ago it was better at both these things.
Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?
#150It became faster and worse. My definite proof is its ability to generate greek content. The early API was generating good or at least passable content. It was really on the edge of "this is good". Now its completely garbage, it makes up words and even fails at basic translation, doing it literally. I think its less the RHFL and more the effort to scale it and make it faster.