srbhr

Hey HN Folks, Back to the drawing board, and earlier this year I've updated Resume Matcher.

This time focusing on: - PDF's text optimisation. - Ensure that extracted text follows a pattern similar to markdown. - And above all, a simple and faster way to optimize your existing resume to a job description, that light nudge with the keywords that makes it fit.

It's not perfect yet, but I'm working towards it more and more. Grateful to have community support so far.

Also, a new website: https://resumematcher.fyi/

+ My oss project site: https://resumematcher.fyi/

https://srbhr.com/

Someone with cheap electricity can serve inference profitably at prices that would bankrupt the current small set of centralized providers.

Strong claim, There's a similar article about China is eating the world on HN. Maybe then, they're the ones who can take over the inference cloud?

That's exactly I was thinking.

I've added a product (SWIRL) it shows 0% off. :) How can I change that?

Not just me, but our team is building: https://github.com/swirlai/swirl-search

We are trying to build an AI metasearch engine that does RAG and Chat based on your office documents. Without any ETL or a vector database.

Thank you, good sir : ) for the explanation.

Thank you : )

Can you please give insights into "Studying topics from first principles instead of corporate documentation"? Studying topics from first principles?

You can try: https://github.com/swirlai/swirl-search

- doesn't indexes data - has connectors to various apps - metasearch under the hood - re-ranking of search results before RAG

This is awesome. However, I'm waiting for a 3.5 Opus. Wonder what happened to that one.

You could try SWIRL Search. I have found API integration from different apps without ETL pretty good. https://github.com/swirlai/swirl-search

It sounds more like a chore. Read, write, note things down. And then re-view your cards/notes over and over. There has to be a short term goal associated like an upcoming exam, interview, etc. for spaced repetition. Although I'm lazy. :)

Talking about primes,(2^136279841)-1 is the New Largest Known Prime Number. Discovered 21st Oct (Today).

Ref. https://www.mersenne.org/

That's the best!

I really like these doom ports. As if they've become a standard to learn, try something new and let others test it out. We had entirely AI generated DOOM and now DOOM for quantum computer. Maybe let's try a Doom in Go which is fully CLI? :-)

Yes, I'm hosting my (first) personal website with it.

Interesting concept. How did you arrive at this idea?

https://sourcemaking.com/design_patterns This is also a good source for learning Design Patterns. Both websites have good examples. I also had gone through a course by Mosh. He explains really well. Link: https://codewithmosh.com/p/design-patterns

https://refactoring.guru/ has some good resources with code provided in multiple languages.

Thank you for creating this. I was looking for something like this some time ago. <3

Hey, this is interesting. We've already seen UI/Web Dev as a Service coming up. (Some of them are doing a nice job). And the idea behind this sounds amazing as well. But I've got a question. In your FAQs, you mentioned that:

"you may not always have enough work to keep them busy at all times"

Can you elaborate further? Why do you think DevOps people might not be busy most of their time?

It is an interesting article, and a good question, "What can AI never do?" There is an ongoing debate on LLMs and Trust, that we should take a look at as well. How much we can trust LLM and the data to make decisions. :)

There is another interesting thing on YouTube. You will see a page loading bar right below the navbar when you load a page. It goes to 75% quickly and then throttles until the page loads. Making the user feel something is working. I've noticed that behavior a lot of times.

indistinguishable intelligent clones (IIC) I like the idea of this. Having mentors to provide targeted advice.

Thank you, this is really cool!

The idea around a testing framework for LLMs is nice. Can you provide some examples where this can be used?

Hey, does it work only in LA?

Can you explain the idea behind a cloud-oriented programming language? How does it works?