41–50 of 752 posts
Generally rewriting emails for clarity... but I found another neat use of GPT-4. For public APIs, I ask to make sure its aware of the api. Then I ask for endpoints. I find the endpoint I want. Then I ask it to code a request to the endpoint in language X (Ruby, Python, Elixir). It then gives me a starting point to jump off from. Thirty seconds of prompt writing saves me about 20 minutes of getting setup. Yes, I have…
I find ChatGPT most helpful as a "what's that called" tool. A lot of my queries are finding/confirming the right idiom when writing something, or getting a specific name out of a vague description (JavaScript concepts, shell commands, CSS selectors). Search engines with SEO are so reliant on keywords that it often feels like I'm suggesting answers rather than asking questions - it's so refreshing to be able to just a…
It's replaced Google for the "what's that called" tool. Google used to be good at that task, but it's sucked for the last four years or so. Whenever they gave up on search and leaned into sludge content plus ads. ChatGPT is better than Google ever was anyway.
Mostly just asking stuff directly on https://chat.openai.com/chat . Last 8 requests were (all successful): - Asked it to improve a HN comment I wrote. - Asked about an idiom I couldn't remember, by saying it in other words. - Asked it to dumb down some things about options (finance) I didn't understand. - Asked it if I could use the eBay API to list my purchase history (you can, and it knew how). - Asked it to genera…
Completely off-topic, but do you like prisma, and how are you using it (scale, complexity, solo vs team, etc). I toyed around with it a while back, and it looked potentially awesome, but different enough that I was worried about using it on a work project in case it failed in some use case. Im so sick of the SQL ORM situation in Typescript, but Prisma might have an answer.
Segmentation fault with NodeJS 18. Its about prisma having linked a different version of OpenSSL than NodeJS. A workaround is to use the "binary" engine, meaning you run another process, talk via IPC to that, and that then talks to the DB, which is ridiculously roundabout.
But this issue is finally worked on, so once that is fixed its good.
I'm also working on a UX for AI to make people more productive when creating things: https://inventai.xyz. Subscriptions are nearly done, which are needed to actually generate content.
Generally rewriting emails for clarity... but I found another neat use of GPT-4. For public APIs, I ask to make sure its aware of the api. Then I ask for endpoints. I find the endpoint I want. Then I ask it to code a request to the endpoint in language X (Ruby, Python, Elixir). It then gives me a starting point to jump off from. Thirty seconds of prompt writing saves me about 20 minutes of getting setup. Yes, I have…
With the understanding that it's only trained up to Sep 2021, I'm using it to spot check for any libraries that have flown under my radar, or any other methods of doing work that I usually do, but in a different fashion. Do I always get stuff that I can apply? No, not really. But given that discoverability can be low for things like that, it's usually helpful at finding me things to, at the very least, look into.
as an fyi its hallucinated libraries for me when writing python code, importing things that dont exist.
A while back, I mentioned in a thread that I have found ChatGPT to be quite useful for correcting grammar and spelling errors ( https://news.ycombinator.com/item?id=34781888 ). Later, when they released their API, I developed a CLI tool for this purpose ( https://github.com/pncnmnp/grammatical ). Note that it is not flawless, but it works well. It has improved my writing productivity, both for blogging and emails.
I like your prompts for your script, I may integrate it into my workflow too. I have found that when I am editing my work, it is helpful to have the original sentence and the suggested sentence one after another. While this takes away the paragraph form, it clearly helps you tease out the "improvements" to either accept or reject. I also have GPT number the sentences. And then when I am done, I say - something like -…
To be honest, my work style can be a bit lazy at times, and this may reflect in my approach. My tool simply copies any changes directly to the clipboard. I then replace them with the original text and make adjustments on the same page. However, for more complex workflows, your approach is awesome. It could potentially transform the process into something similar to Grammarly.
Edit: Have you noticed any differences in terms of quality between GPT-4 and Turbo3.5 for this particular task?
So far only using the free version and experience is good. I might buy the plus subscription but so far lacking any hard requirements. I particularly hope it gets better teaching me system programming as sometimes it BS.
At the end of the day, none of the output it’s offered has necessarily impressed me, though some of the ideas from that output has influenced me an how I write my resume.
I also tried to see if could generate come code similar to something I used in a recent side project. It utterly failed to produced correct code, but perhaps the gpt4 model would do better. So far I’ve been using it as search engine as I will admit, it’s done better than google and friends at giving me the information I ask for,