The whole reason I come to HN in the first place is to filter out BS clickbait articles exactly like this one, not to have them fill the front page.
2,076 karma · joined December 30, 2022
The whole reason I come to HN in the first place is to filter out BS clickbait articles exactly like this one, not to have them fill the front page.
- You have zero engineering background and you use an LLM to build an MVP from scratch. As long as the MVP is sufficiently simple there is plenty of training data for LLM to do well. E.g. some kind of React website with a simple REST API backend. This works as long as the app is simple enough, but it'll start breaking down as the app becomes more complex and requires domain-specific business knowledge or more sophisticated engineering techniques. Because you don't understand what the LLM is doing, you can't debug or extend any of it.
- You are an experienced developer and know EXACTLY what you want. You then use an LLM to write all the boilerplate for you. I was surprised at how much of my daily engineering work is actually just boilerplate. Using an LLM has made me a significantly more productive. This only works if you know what you're doing, can spot mistakes immediately, and can describe in detail HOW an LLM should be doing the task.
For use cases in middle, LLMs kind of suck.
So I think the comparison to a (very) junior engineer is quit apt. If the task is simple you can just let them do it. If the task is hard or requires a lot of context, you need to give them step by step instructions on how to go about it, and that requires that you know how to do it yourself.
Yeah, with Deepseek the barrier to entry has become significantly lower now. That's good, and hopefully more competition will come. But it's not like it's a fundamental change of where the secret sauce is.
What we need is an easier way to verify sources and their trustworthiness. I don't want an answer according to SEO spam. I want to form my own opinion based on a range of trustworthy sources or opinions of people I trust.
4. Skimming HN is useful in text-format because you can go deeper on something that catches your eye by following the link. The podcast format removes this because you can't click on something you hear and dive deeper into it. Skimming without the ability to dive into something is not useful, see next point.
5. High-level summaries are not my use case for HN, or any social media. They don't provide real value, just the illusion of value. What I want to dive deep into stories I am curious about. That can be done with TTS, but I would need to curate my feed first, and then use the podcast format to dive deeper into my curated stories.
I almost feel like this product would be more useful if you remove the LLM aspect and instead let me paste a list of HN threads into it and just TTS all of them, including the full comments. Then I could listen to this long-form content while driving or doing something else.
I don't know what the solution here is. My guess is that the "public internet" will become less and less relevant over time as it becomes overrun by low-quality content, and a lot of communication will move to smaller communities that rely heavily verifying human identity and credentials.
Reading the Selfish Gene today as an adult, when you've probably read a dozen similar books already, is not going to have the same effect. It's going to be pretty boring. That's why asking for book recommendations is flawed to begin with.
Some people don't like the term, but at least with JRPGs you know pretty much exactly what they are. Any other RPG term is completely meaningless because it's way too broad.
- Learn Nix
- Homebrew can be a pain. I've had several occasions where it broke something on my system with its magic. The main reason for this is its imperative (as opposed to declarative) nature. You can easily install things that clash with other software installed on your system.
- You can easily install different versions of the same software without having to worry about clashes
- Fully declarative configuration. You know exactly what is installed on your system at any time.
- Portable reproducible configuration. Imagine you get a new laptop. Because you have have your system configuration declared with nix and home-manager you can copy the configuration file, run install, and your system is set up, exactly the way the old one was.
- To add to the above, you can also do the same with non-MacOS systems if you make your config conditional on MacOS. I sometimes want to work on a remote Linux machine. I can set up a full dev environment with all the tools I use locally with a single command now.
Of course, I can ignore anything I am not interested in. But the reality of the situation is that out of 30 minutes reading RSS feeds I spend 20 minutes filtering out stuff I am not interested in. Also, crucial information such as post popularity is missing because it's not available at publishing time and changes over time. "Social" is not part of the protocol.
You can argue that social media sites don't belong into RSS, but then you are removing the single biggest use case of RSS. If I can't put social media feeds into RSS it's useless to me because social media is exactly what overwhelms you with information and FOMO, which is what RSS should be solving.
I'm aware that serialization frameworks like protocol buffers do this, but they usually come with a whole lot of other baggage, dependencies, hit-or-miss language support, and clunky APIs. I want something more lightweight that allows me to start developing an application by developing its schema, without it being tied to a specific serialization framework or language implementation.