Hacker News Reader

I believe you can achieve that with n8n. Used in past (and still running) for some data transformation and little more. Possibly similar case what are you describing.

https://n8n.io/ https://github.com/n8n-io/n8n

throwaway888abcon Show HN: I was tired of low-quality AI content, so I built a better version

Google no longer accept those. I think from 5 Mar ?

https://blog.google/products/search/google-search-update-mar...

throwaway888abcon Ask HN: Freelancers, how do you successfully expand to new markets?

Not to take your candies off - wish you very best and hope you make it.

"through an agency" - is completely different situation than on your own from buyer perspective.

> Those clients were very impressed with my work.

Ask them to hire you directly as freelancer or ask them to refer (you can also optionally compensate for referral) you some work. Easy to make and effective.

Good luck

throwaway888abcon GPT-4 matches radiologists in detecting errors in radiology reports

Study:

https://pubs.rsna.org/doi/10.1148/radiol.232714

throwaway888abcon Show HN: Storing Private Keys in the Browser Securely

Hat off, You made it! After reading and skimming Show HN: Device-Bound Session Tokens in JavaScript ( https://news.ycombinator.com/item?id=40052684 ) I had "same" idea to explore PoC, but never done. Thanks!

throwaway888abcon Ask HN: How do you optimize Google search for good long-form technical content?

You don't need to. Google deliver it optimized via SGE.

https://blog.google/products/search/generative-ai-search/

throwaway888abcon I can't stand using VSCode so I wrote my own

Thanks for tip, TIL

throwaway888abcon Earth Online: non-stop satellite monitoring platform

Paywall ? (As one word)

throwaway888abcon Cosine.club: A music similarity search engine

Beautiful, thanks! Just go new playlist

throwaway888abcon Ask HN: Are there AI prompt builder products?

Logitech just build it into mouse.

https://www.logitech.com/en-us/software/logi-ai-prompt-build...

https://blog.logitech.com/2024/04/17/looking-to-improve-your...

throwaway888abcon Limitless: Personalized AI powered by what you've seen, said, and heard

1984 by accidental convenience

throwaway888abcon Show HN: Reduce ChatGPT costs 10x with distributed cache for LLMs

>We are still exploring. Fair point. Worth of looking into, is to create/train/tune small model (2b/7b) based on previous cached answers in case your knowledge index/domain is without changes in time.

Exciting times

throwaway888abcon Show HN: Reduce ChatGPT costs 10x with distributed cache for LLMs

Looks great, do you have any concrete data how much money it will save ?

Also, how does it compare to for example GptCache[0] ? or any other semantic cache solution[1] ?

[0] https://gptcache.readthedocs.io/en/latest/

[1] https://portkey.ai/blog/reducing-llm-costs-and-latency-seman...

throwaway888abcon InfLLM: LLMs for Understanding Long Sequences with Training-Free Memory

Paper: InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory

https://arxiv.org/abs/2402.04617