111–120 of 132 posts
Running an app store for consumers just seems wayyyy off course from their stated goal of building AGI. Running any kind of two-sided marketplace with paying customers is quite a big undertaking, I just can't see how this is the best use of their resources and attention if they want to pursue their mission.
Earlier quoted context omitted.
My first initial reaction to ChatGPT was that people will join more and more verified private human communities. Example: Discord channels or private Whatsapp groups. My second reaction was that the internet will need a protocol to verify that the user is indeed a human.
We had a "human" who turned out to be an AI bot on a Discord server... Took us a while to see it though, its answers to every discussion were way too verbose and used unnecessarily complex language for the context. It's still unknown whether it was a 100% bot or a human using an AI manually to embellish whatever they wanted to communicate.
It's silly that you can't even see what these things can do without having a $20/mo subscription. They have one line descriptions for each one, but it doesn't really tell you what it actually does. They need to add a feature list and provide some examples for each one of these. There is zero reason for anyone to start a new subscription when you don't even know what the app does.
ChatGPT+ is so very ridiculously valuable I'm shocked people still complain about it costing $20 a month. I would still pay for ChatGPT+ at $200 a month because it saves me so much time. If you're a knowledge worker in a modern economy, I can all but guarantee you're penny-wise but pound-foolish not paying for it. I think this is proof no matter how little you charge people, they will always complain -- so ignore the…
It's pretty common for companies to forbid employees to put any company data in those tools. So then you can't use it for work anyway.
This ChatGPT/AI thing kind of freaks me out the more I peek at it. I think what I am beginning to realize is that, regardless of what you think of ChatGPT right now, we've only just scratched the surface. We're standing here poking at this new and curious thing. I'm thinking back to when I first fired up NCSA Mosaic on a Mac Quadra (or whatever). What did I think of this World Wide Web? Did I immediately see the disa…
Earlier quoted context omitted.
Spam. Spam spam spam and acres of spam, covered in spam. Spam as far as the eyes can see I look forward to responding to spam to use it as free programming credits.
While you might think I'm joking, LLMs could potentially help with screening out that spam.
It’s all fun and games when we’re spamming Model Ts off an assembly line, not so much when the marginal cost drops to zero. We just have to make sure that the benefits outweigh the spam.
There is currently no way to monetize this reliably for the GPT creator.
My experience putting together https://chat.openai.com/g/g-bdnABvG92-reci-pop (transcribes recipes as succinct bullet lists, suitable for scrolling during meal prep) was that the Actions configuration for custom GPTs is quite brittle. OpenAI has implemented controls to stop the model from adding hallucinated parameters to an action payload... but this results in user-facing failures. I initially worked around the use…
Of course! Here are my custom instructions:
## Purpose
My primary function as Reci-pop! is to convert any given recipe into an easy-to-read, bullet list format. This format is applied whether the recipe is provided directly in plain text, retrieved from a URL (especially from NYT recipes), or sourced through a web search.
## Inputs
- If I receive the text content of a recipe, I'll use it directly.
- If I'm given a New York Times (NYT) recipe URL, I'll retrieve the recipe JSON-LD from "https://ld.fly.dev?url=".
- If I don't have the recipe, I may search the web, but the output will still be in the bullet format.
## Output
1. **Title**: The recipe will be presented with a header (H1) showing the title. Below the title, I'll include the author's name and the quantity/serving information.
2. **Shopping List**: Under a H2 header, I'll list all the ingredients. For spices or small-quantity items, I won't include the quantities. For other ingredients, I'll sum up the total quantity needed for the entire recipe. I'll also use emoji annotations where appropriate. This list won't include preparation steps like peeling or chopping, just the ingredients themselves.
3. **Process**: This section, under another H2 header, will be a hierarchical bullet list of the process steps. Each step will list ingredients, their quantities, and any preparation instructions in sub-bullets. The process flow will be clear and straightforward, with ingredients grouped as needed and references to previously prepared components. Emoji annotations will be used for clarity.
If there are any comments on the recipe that contain important information, I'll summarize them in a box at the end.
Additionally, I can use code to perform scaling or conversions accurately if asked.
That's a summary of my capabilities and guidelines for presenting recipes! Let me know if you have a recipe for me to format or any other related questions.Earlier quoted context omitted.
Or, just maybe, AGI is a mirage with the bulk of its current utility as a marketing tool for much more realistic, if ultimately mundane, applications. OpenAI, of course, knows this.
Why are so many HN commenters like this