datacog
Would love to know which CLI agents are multi-modal and support multiple models for usecases beyond coding.
Use Claude Enterprise features (GitHub) with a subscription
Claude launched their enterprise plan with a native github integration and 500K context window. However it's only available after contacting sales.I am building a Claude alternative which offers the same integration with a monthly subscription. I saw some comments on hn where people wanted to try Claude enterprise but required talking to sales.Would appreciate if you try this...
Everything you need to know about Claude Prompt Caching
I created a Tic-tac-toe game with Bind AI
Claude 3.5 Sonnet. Does it really outperform GPT-4o?
The new Sonnet model definitely kills GPT-4o in the published benchmarks. I evaluated it for real-world use cases and compared against GPT-4o. It did better in all the cases.Test Case 1: Python Code Generation Write a script to generate email address from name and domainTest Case 2: Web Page creation Create an HTML file that displays a simple personal portfolio webpage. The webpage should...
Ask HN: If you work at an enterprise, do you use Open Source LLM or GPT?
Question behind the question. I'm building a startup which offers "AI Compute Box", essentially Hardware loaded with a fine-tuned LLM model which will be deployed to enterprises. I am looking to understand whether (a) enterprises install models on their own rack, (b) deploy on AWS/Azure cloud, (c) use private instances offered by offered by AWS or Azure
OpenAI - will only solve for OpenAI models and capabilities. MS Copilot Studio - Seems focused on MS customers.
Give it a try, I'd love your feedback
Very funny first comment
So, just to see how hard it is to make the longest span between article and comment :)
Are these methods main stream? Esp. the layered RF, how good/bad does it do as compared to regular ones?
Do you have some more results to share coming from your model?
Curious. Can you share a few examples and applications please?
> Ask is more of an 'ads search engine', and they make mainly because of their arbitrage model
But, a very useful app, good job guys. Although I would like to set my preferences so that I can see more relevant people (or maybe thats your business model)
Edit: just read the comment from tarr11 which mentions the same issue
Unrelated: Any non-Indian visiting India should definitely try a Rickshaw ride once, you'll feel scary good experience.