vb7132

Isn’t a cosine similarity over the text embeddings a much more effective way to handle categorization?

The whole reason why embeddings work so well is because they encode the underlying meaning of the texts

This is a very cool idea. If it wasn’t .net, I would love to re-use it for my own use cases.

The comments can be even more interesting and thought provoking than the post

I love this ending. I don't agree with author's views. But the article is very coherent, thought provoking. And definitely the comments here on HN are even more interesting.

Couldn't agree more. The opportunity cost of executing something is maintaining it. And that's where the real cost lies.

Big companies won't execute our ideas because they need maintain everything that they execute. Plus, the cost of modifying something that was executed itself is also very high at a big company.

Having managed developers for over five years, I have seen two categories of devs (to simplify the argument, let's focus just on the smart ones):

- one group loves to work independently and gets you the results, they are fast and they figure things out

- second group needs direction, they can be creative in their space but check-ins and course corrections are needed.

AI feels like group1 but it's actually group2. In essence, it doesn't fully fit in either group. I am still figuring out this third group.

True, there are people who are good with people. And they should totally become managers.

But there are also the third kind: who like to design the systems and let them be built by someone else..

Same level of engineer here - I feel that the importance of expertise has only increased, just that the language has changed. Think about the engineer who was an expert in Cobol and Fortran but didn't catch the C++ / Java wave. What would you say to them?

LLMs goof up, hallucinate, make many mistakes - especially in design or architecting phase. That's where the experience truly shines.

Plus, it let's you integrate things that you aren't good at (UI for me).

Yes, you are right: amongst the four points, migration is the most contentious one. You need to be fairly prudent about migration and depending on the project complexity, it may or may not work.

But I do feel this is a solvable problem long term.

Very valid point. I will lay down the facts for you:

At my previous employer, I was generating $2.5million per year (revenue per employee). I didn't ship a single line of code. All the time was spent trying to convince various stake holders.

Now, I have already built a couple of apps that help me better manage my tech news (keeps me sane) plus I am writing a blog that generates $0. It's only been a month.

If you measure the immediate dollar value, you are right. But in life, pay-offs are not always realized immediately. Just my opinion anyway.

I was at a big tech for last 10 years, quit my job last month - I feel 50x more productive outside than inside.

Here is my take on AI's impact on productivity:

First let's review what are LLMs objectively good at: 1. Writing boiler plate code 2. Translating between two different coding languages (migration) 3. Learning new things: Summarizing knowledge, explaining concepts 4. Documentation, menial tasks

At a big tech product company #1 #2 #3 are not as frequent as one would think - most of the time is spent in meetings and meetings about meetings. Things move slowly - it's designed to be like that. Majority devs are working on integrating systems - whatever their manager sold to their manager and so on. The only time AI really helped me at my job was when I did a one-week hackathon. Outside of that, integrations of AI felt like more work rather than less - without much productivity boost.

Outside, it has proven to be a real productivity boost for me. It checks all the four boxes. Plus, I don't have to worry about legal, integrations, production bugs (eventually those will come).

So, depends who you are asking -- it is a huge game changer (or not).

  IMO, the writer is overzealous with their comments on LLMs. As a coder, it feels like an outsider trying out a product that was amazed me over and over so many times.

  > They aren’t perfect, but the kind of analysis the program is able to do is past the point where technology looks like magic.

  But as you use this product over a long period of time, there are many obvious gaps - hallucinations / repeated tool calls / out of context outputs / etc.

  To me, refine.ink sounds like a company that has built heavy tooling around some super high context window LLMs and then some very good prompts. Their claim is to compare it against any good off-the-shelf LLM with any prompt. But when you are spending bunch of money to build a whole ecosystem around LLMs, it's obvious that it's not going to beat their output. 

  I won't be surprised if the next version of an LLM within the next few months completely outperforms their output -- that's usually the case with all the coding tools and scaffoldings. They are rendered useless by a superior LLM.

Your discord link doesn't seem to work. One basic question: As a hardware noob, where do I start? Maybe having a minimal getting started guide could really help.

Nevertheless, the initiative looks cool!

A link to my experiment: https://www.bvaibhav.info/knos-digest

This is fantastic. The app is simple, useful and feels de-cluttered.

Two of my feature requests: 1. Allow cmd+f search on the whole app - I wanted to search your post on the app but I couldn't 2. A browser button to open the current page on an external browser.

Side note: I am trying to minimize my HN time via getting push notifications for relevant HN posts, and that's how I discovered your post. Would it be cool if one could write custom agents on top of an app? Maybe?

This feature is very useful :)

This seems like a common problem. I am experimenting with how to consume less news (but still not miss the important bits). Built an agent that sends me daily summaries. And that's how I found this post!

I am maintaining the list of what I am reading: https://www.bvaibhav.info/knos-digest

Plan to extend this beyond HN.

This is an awesome. I had a similar one: Convert the dense non-fiction books into something more readable. eg. SAPIENS vs UNSTOPPABLE US.

But this makes me wonder: What is the barrier to entry for these apps now? Anyone can do it. There is going to be a barrage of apps/websites like this?

After working at the same (big tech) company for nine years, I feel like an outlier. My career has had phases of intense hard work and periods of rest. However, my happiness was influenced by many other factors. While working hard and being in the flow can be incredibly gratifying, it can also be stressful. Additionally, the relationships at work play a significant role, more so than the work itself.

In my friend circle, I’ve noticed that the happiest people are those who are pursuing their own interests and achieving moderate success in them. Ultimately, this seems to create a sense of purpose. And I am envious of such people.

Work is also a crucial component of the "work-life" balance dichotomy. If you’re not working enough, you’re likely to feel unhappy.