Live data from Hacker News

Ask HN: How are you using GPT to be productive?

news.ycombinator.com

221–230 of 752 posts

Re: Ask HN: How are you using GPT to be productive?

#221
post #177

Earlier quoted context omitted.

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…

> I don't think it's actually reasoning about things at all, just providing a statistically plausible response to prompts. It turns out that humanity’s problem might not be that AIs can think but rather that humans believe that AIs can think. One might even go so far as to say there’s a real danger that we hallucinate that AIs can think, to our detriment.

We don’t actually know what “thinking” is, though, so I’m not sure it’s possible to say “this model can’t think”.

Re: Ask HN: How are you using GPT to be productive?

#223
post #218

Follow up question, how come discussions like this rarely mention virtual assistants like Siri/Alexa/etc? So many use cases overlap, there’s potential for improvements but Siri still struggles to understand context and gpt has no way to access my calendar (at least in a way that I’d like). I guess this will change fast?

Whisper and HomeAssistant might do it.

I bet it'll be a nightmarish fiddly project.

Re: Ask HN: How are you using GPT to be productive?

#224

So much: - generate AWK to transform text - modify python script to make it multithreaded (when this worked first go I was very mindblown) - explain concepts that I half understand in clear language, eg explain sharpe ratio and show me the math - “what do people usually call” type questions. Like what are common job titles for people who do X and Y? - proof read my emails and make suggestions given a stated goal - se…

I'm curious what you mean by "reverse pitch understanding" in your second last point, could you elaborate?

I had the same question, and I asked GPT-4: https://pastebin.com/9RxenXMk

The phrase has zero hits on Google, though “reverse pitching” is apparently a thing.

Re: Ask HN: How are you using GPT to be productive?

#225

So much: - generate AWK to transform text - modify python script to make it multithreaded (when this worked first go I was very mindblown) - explain concepts that I half understand in clear language, eg explain sharpe ratio and show me the math - “what do people usually call” type questions. Like what are common job titles for people who do X and Y? - proof read my emails and make suggestions given a stated goal - se…

> modify python script to make it multithreaded (when this worked first go I was very mindblown)

Sounds intriguing, could you elaborate? Which gpt did you use? What was the input like and what did the gpt produce?

Re: Ask HN: How are you using GPT to be productive?

#226

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…

Yea, this is great. I used it alot for this. When you kind of know what you wanna do but you dont know the technical term.

Like if you dont know it is called sharding but you know you wanna store stuff on several databases.

Me: I have a postgresql database but it has too much data in it. I wanna split the data in several databases. What is that called?

GTP: Splitting a database into multiple smaller databases is known as database sharding. Sharding is a technique used to horizontally partition large databases across multiple servers or instances in order to distribute the workload and improve performance. Each shard is typically hosted on a separate physical or virtual machine and stores a subset of the total data, allowing for more efficient queries and faster data retrieval.

Then i know what to google for

Re: Ask HN: How are you using GPT to be productive?

#228

I have found it is quite good at configuring complex AWS IAM policies in JSON. Not perfect but it saved a bunch of time. There are so many other examples but I truly never reach to google first anymore.

Uff, how do you verify these? One forgotten slash and you have exposed more areas than you wanted.

Re: Ask HN: How are you using GPT to be productive?

#229
Encouraged by the comments here, I tried a few prompts for it to do something useful for our company. Most failed, but it's apparently great at improving our documentation. Here's the prompt and the result as an example:

> Can you improve the following text for clarity: "When deploying into the enterprise, there is a lot of flexibility when it comes to deciding how you structure the deployment, whether you want to run supporting services on premise, and which ones (if any) you choose to deploy. The decisions depend on how you plan to use our software and your security requirements. We’ll be happy to discuss these with you at [email]."

Result:

> "When deploying our software into your enterprise, you have the flexibility to decide on the structure of the deployment, including running supporting services on premise and selecting which ones (if any) to deploy. Your decisions should be based on your intended use of our software and your security requirements. If you need help with these decisions, please feel free to contact us at [email]"

It did indeed improve clarity and readability without screwing anything up. I just want to run this thing on our whole website/repo now, and I wonder how.

Re: Ask HN: How are you using GPT to be productive?

#230
post #123

Since I use ChatGPT regularly, I decided to create my own client. I prefer to avoid third-party services that require privilege escalation like Grammarly and Copilot. I have developed distinct profiles for different tasks, each with its own system prompt and input method. After getting the hang of it, I plan to tweak the parameters as well. Here are some of the profiles: Explainer: a default, general purpose Q&A. The…

Thank you, I intend on stealing your phrase "skip prose", was trying to find a way to force it to exclude this whilst saving tokens.

I’m unfamiliar with gpt and tokens, what would “skip prose” change?
Post reply on HN