My most common usage now is asking it to come up with names for functions/classes.
You can iterate on the names it come up by telling it why you don't like the names it proposed.
Ask HN: How are you using GPT to be productive?
271–280 of 752 posts
Re: Ask HN: How are you using GPT to be productive?
#272For doing simple tasks such as help writing unit tests.
I need to often give some examples from other tests. I need to make many edits, but it spits out enough to have a basic boilerplate-ish template and speeds up my work by at least ~25%.
Re: Ask HN: How are you using GPT to be productive?
#273I might be in the minority here, but I'm not using any AI tools so far, probably to my detriment. I don't trust it with my data, and won't rely on such tools until I can self-host them, and they can be entirely offline. There is some progress in this space, but they're not great yet, and I don't have the resources to run them. I'm hoping that the requirements will go down, or I might just host it on a cloud provider.…
Me neither, but I think before long people like us are going to be left behind. We're like people who insist on continuing to ride horses in the age of the automobile.
I think that time will come, but we'll have self-hosted options before employers start discriminating based on performance with or without AI tools. So I'm not too worried about it.
Re: Ask HN: How are you using GPT to be productive?
#274bing for browsing and solving problems in code or otherwise. I still use a my old Brave browser for Youtube and most other browsing still.
I will probably start using ChatGPT again now that theyre adding plugin support
Re: Ask HN: How are you using GPT to be productive?
#275Earlier quoted context omitted.
So on my coding problems I haven't had much luck. It doesn't seem to know Bazel, the Rust code I asked about was completely hallucinated, but it did solve a problem with Azure DevOps I had. I think if the training set did not contain enough of something it can't really think of a solution. What is really nice though it's as you say the refinement of questions. Sometimes it's hard to think of the right query, maybe yo…
Yeah, I gave it a simple task of encoding a secret message in a sentence by using the first letter of every word. Hello = "Hey everyone, lick less onions". I worked with the prompts for over an hour to try to get it to complete the task, and while I did have some success, it really struggled to reason about the task or provide a valid response. If it can't even reason about a child's game, I can imagine it struggles…
Is this with Chatgpt or GPT4? The latter is supposed to be way, way better, according to this paper[1]
Re: Ask HN: How are you using GPT to be productive?
#276Earlier quoted context omitted.
We don’t actually know what “thinking” is, though, so I’m not sure it’s possible to say “this model can’t think”.
> We don’t actually know what “thinking” is How about: thinking is to make sense of the world (in general) and decide how to respond to it.
Ai definitely senses and definitely makes decisions. It does not feel. But it understands concepts. Just like people don’t understand everything—and you can test them to see what they understand—AI understanding can also be assessed with benchmarks. If we don’t base AI understanding on benchmarks, then we don’t really have a grounding.
Re: Ask HN: How are you using GPT to be productive?
#277Earlier quoted context omitted.
My advice to learn programming is to avoid shortcuts and do the hard things like read the documentation
Bro documentation is notoriously terrible in almost all spaces. Gpt3.5 is like super Google, and gpt-4 is like a polymath in everything intern. Learning has never been easier for me, I'm stoked.
Also documentation is, how to say, heavily styled in a sense.
If you disliked a certain teaching style before you were basically screwed. I've learned some languages purely because the documentation was fun for me personally.
Re: Ask HN: How are you using GPT to be productive?
#278I've had some great uses. I've had it clean up language in customer facing documentation, had it provide great examples for things like KPIs and OKRs, I also had it take a story about a beloved pet and write prompts for a children's book.
I haven't used it for coding but I've definitely found it really useful in writing. I'm not a bad writer, when I put thought into it but I find it's always useful to have a collaborator and ChatGPT has given me one that's always available.
I've also done some less productive things like work out architectural plans for a chicken coop remodel I need to do. I also got into a discussion about where and how to do french drains on my property, so we can plant more.
Re: Ask HN: How are you using GPT to be productive?
#279[dead]
Re: Ask HN: How are you using GPT to be productive?
#280I tried, not actually at work but for something open source, to get it to help me rework a terraform provider using the old SDK to use the new 'framework' - I've only ever written Go for terraform providers (and that not much) so I often have dumb confusions about how to do something that end up more about Go than the API itself, it's just not necessarily obvious initially, or what to search for etc., so I thought it was a great opportunity.
It didn't really work though - it produced something extremely plausible looking that checking against the docs I realised had no chance of compiling. After a lot of back and forth, I began to suspect it was because it was trained while only pre-1.0 versions of the 'framework' were available. I tried to get it to confirm that, but it just apologised profusely while continuing to lie, claiming to have been trained with access to 1.x versions that to this day have not been released. At this point I was too frustrated to bother with it anyway really, but I could only confirm my suspicion by asking it for the date of its training, and checking release history myself.
(Solved my problems with some good old 'ChatHuman' in the Hashicorp forum.)