Hacker News Reader

esha_manideepon Ask HN: Cursor or Windsurf?

Latest cursor update where they started charging for tokens is pretty good. I don't use non-MAX mode on cursor anymore

esha_manideepon A flat pricing subscription for Claude Code

Claude's limits are so vague - its not clear if buying Claude Max is cheaper than just using the API. Has anyone benchmarked this?

esha_manideepon Perplexity AI is lying about their user agent

They check after they scrape

esha_manideepon Show HN: Tarsier – Vision utilities for web interaction agents

Great work guys! How did you benchmark traiser's 10-20% better? Would love to see exactly how each method scored

esha_manideepon InternLM2

Pretty amazing to see training data being discussed more openly

esha_manideepon The Era of 1-bit LLMs: ternary parameters for cost-effective computing

These models will are compatible with llama.cpp out of the box, we (GigaML - https://gigaml.com) are planning to train a small model (3-4B, 1-bit, opensource) with the latest stack-v2 dataset released today. Let me know if anyone is interested in collaborating with us.

esha_manideepon Chrome experimental AI features

Having a feature to summarise the website would be a much better than the first two. As I constantly find myself wishing for such a feature :/