cosmtrek

Joined 9 years ago

Karma

67

Submissions

18

Member since

Jan 19

View on Hacker News

Recent submissions

Comment · 3 months ago

Glyph3D looks cool! I'll look into it and give it a try as soon as I can.

Comment · 3 months ago

MIT. I've added it. Have fun!

Comment · 3 months ago

Much appreciated. That said, I think we may have different use cases. My goal is to solve the problem of inspecting and evaluating how LLMs and agents perform tasks. This project could draw inspiration from Anthropic's research: https://www.anthropic.com/research/global-workspace. It's just the beginning, and there are lots of things to improve. :)

Comment · 3 months ago

Thanks bro, you see the value of this project!

Comment · 3 months ago

My original motivation is to compare the task-solving ability of LLMs by visualizing the agent's trajectory. This offers an alternative way to inspect the capabilities of LLMs and agent systems.

Comment · 3 months ago

My original motivation is to compare the task-solving ability of LLMs by visualizing the agent's trajectory. This offers an alternative way to inspect the capabilities of LLMs and agent systems.

Comment · 3 months ago

Wow, it's my first time learning it. The visualization seems similar.

Comment · 3 months ago

Thanks for your thought!

Comment · 3 months ago

Comment · 3 months ago

Thanks, added to my backlog~

Show HN: Mindwalk – Replay coding-agent sessions on a 3D map of your codebase github.com

162 cosmtrek 3 months ago 63 comments

Show HN: Jeju – a local-first agent harness with inspectable runs github.com

1 cosmtrek 5 months ago 0 comments

Comment · 3 years ago

IMO, It's full but not focused on developer services. Thanks for your response anyway.

Comment · 3 years ago

Got it. Thank you for handling it.