Hacker News Reader

you gotta appreciate claude

idoshon Show HN: Engineering.fyi – Search across tech engineering blogs in one place

you can go directly to our webapp https://app.daily.dev. Btw, the extension is open source so you can see nothing is sketchy: https://github.com/dailydotdev/apps/

idoshon Show HN: Engineering.fyi – Search across tech engineering blogs in one place

Shameless plug, you can find all of them and many more on https://daily.dev/. It's a personalized aggregator for developer news

idoshon Use Your Product

oh no doubt... got amazed by seeing some people use my product

idoshon Automerge-Repo: A "batteries-included" toolkit for local-first applications

How is it compared replicache, watermelondb and the rest?

idoshon The 300% Production Problem

Brilliant quotes made me laugh so hard:

> If you’re unlucky, you might read this and think, “holy shit, no wonder I’m burned out”.

> building an operator for everything which is the proposed solution of some people who really just want to watch the world burn.

But actually, the takeaway is this:

> You want simplicity where it benefits the user, which often requires increased complexity for the developer.

Professionals should make it easier for downstream users. In the context of this article, it means the platform engineers should abstract the complexities for application developers to be able to deploy safely their applications

idoshon LangChain for Elixir

It's about time!

idoshon Micromanagement: The Unpopular Truth You Need to Hear

But I think that's the misconception today. Micromanagement is often being confused with just management. Terminology wise I agree with your term

idoshon Fine-tune your own Llama 2 to replace GPT-3.5/4

Thanks! I need to dive into the project and learn more. Sounds exciting

idoshon Fine-tune your own Llama 2 to replace GPT-3.5/4

Can you elaborate on your plans for OpenPipe? Sounds like a very interesting project

idoshon Show HN: Langfuse – Open-source observability and analytics for LLM apps

Congrats on the launch! Sounds like an exciting project. Do you plan to store also the raw data (input + output)? It can be relevant for fine-tuning, optimizing costs, etc. Since you already store metadata, I think it makes sense to have a one-stop shop.

idoshon Human embryo models grown from stem cells

The goal eventually is to be able to create organs in lab condition that can be implanted

idoshon Making sense of React Server Components

How does it handle flaky connection or even offline scenario? How does it work with service worker?

idoshon Vector Search with OpenAI Embeddings: Lucene Is All You Need

We're using Redis for vector search. It's pretty rad in terms of performance and other capabilities