Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 3 min 42 sec ago

Ask HN: What do you think about Devin?

Wed, 03/13/2024 - 3:34am

Anyone can build it with gpt4, then just swap to gpt4.5, it may cost 5k/month for 1 autonomous software engineer, but it will cost zero in a year, I will build Devin in a month if I this thread gets 10 likes

Comments URL: https://news.ycombinator.com/item?id=39688913

Points: 1

# Comments: 0

Categories: Hacker News

Ask HN: Where can I find practical comparative data regarding different LLMs?

Wed, 03/13/2024 - 3:33am

I've been trying to keep up with the advances in the world of AI and LLMs. NLP was a world that I knew pretty well 7 years ago, when I knew most of the major NLP libraries, and their various strengths and weaknesses. However, nowadays, I'm having trouble finding good discussions about the real uses of the LLMs.

I have gone to Hugging Face, and the amount of data there is overwhelming, but it seems poorly organized:

https://huggingface.co

Does anyone know a secret that makes that site tractable? I've experimented with a few of the libraries posted there, but I can only sample a tiny fraction of what is there, and what I'm missing is some method for finding the useful stuff while disposing of the junk.

7 years ago I could tell you the strengths of weaknesses of the Google's Tensorflow or the Stanford NLP library. But where do I go to get good comparative information now, about the strengths and weaknesses of the various libraries that interact with the new LLM tools?

I'm looking to answer practical questions, that I can use in my own work with AI startups.

For an example of a question, for which I cannot find an answer, I am aware of a startup that has developed a chat client that, the startup says, can entirely replace a company's customer support team. Among the claims made by the startup is that when their chat client makes a mistake, it can be easily adjusted so it won't make that mistake any more. I am curious, what approaches are the engineers at that startup probably using to fix mistakes? If I search Hugging Face for ways to fix factual errors in LLMs then I see some libraries, but I've no idea what is considered good or bad.

So I asked the Hacker News community, how are you keeping up with advances around LLMs and associated tools?

Also, every LLM seems to have an embedded finite state machine that remembers the state of the current conversation, so where can I go to learn about the strengths and weaknesses of those finite state machines? How would I go about adjusting them?

Comments URL: https://news.ycombinator.com/item?id=39688911

Points: 2

# Comments: 0

Categories: Hacker News

Show HN: Writ.ly – Easy online Markdown editor

Wed, 03/13/2024 - 3:27am

I absolutely love tldraw; it's a fascinating tool I use every day. And Bear Editor? Can't imagine my life without it. So, I set out to blend the best of both worlds as a toy project :3

I've also modularized the editor (https://github.com/writly/writly) as a React Component. Feel free to give it a try!

Comments URL: https://news.ycombinator.com/item?id=39688869

Points: 3

# Comments: 0

Categories: Hacker News

Before Machine Learning Vol 2 – Calculus

Wed, 03/13/2024 - 3:19am

Article URL: https://www.mldepot.co.uk

Comments URL: https://news.ycombinator.com/item?id=39688823

Points: 1

# Comments: 1

Categories: Hacker News

Give some new links a chance

Wed, 03/13/2024 - 3:15am

Article URL: https://news.ycombinator.com/newest

Comments URL: https://news.ycombinator.com/item?id=39688802

Points: 29

# Comments: 2

Categories: Hacker News

Tenant-aware Serverless Postgres to build SaaS

Wed, 03/13/2024 - 2:43am

Article URL: https://www.thenile.dev/

Comments URL: https://news.ycombinator.com/item?id=39688664

Points: 1

# Comments: 0

Categories: Hacker News

Frugivore

Wed, 03/13/2024 - 2:33am
Categories: Hacker News

Pages