user: xdotli

15 karma | created 2 years ago

Founder BenchFlow.ai, a benchmark company.

recent submissions

Automatically Learning Skills for Coding Agents (gepa-ai.github.io)

4 pts|6 days ago|discuss

We Reached 74.8% on terminal-bench with Terminus-KIRA (krafton-ai.github.io)

2 pts|6 days ago|discuss

(no title)

6 days ago|discuss

(no title)

6 days ago|discuss

Self-generated skills don't do much for AI agents, but human-curated skills do (theregister.com)

2 pts|6 days ago|3 comments

(no title)

12 days ago|discuss

(no title)

12 days ago|discuss

First Agent Skills Hackathon by the Authors of SkillsBench (skillathon.ai)

2 pts|12 days ago|1 comment

(no title)

12 days ago|discuss

(no title)

12 days ago|discuss

The First Agent Skills Benchmark (huggingface.co)

1 pts|12 days ago|1 comment

(no title)

12 days ago|discuss

(no title)

12 days ago|discuss

(no title)

12 days ago|discuss

(no title)

12 days ago|discuss

(no title)

1 month ago|discuss

(no title)

2 months ago|discuss

(no title)

2 months ago|discuss

GPT-5.2 got worse on Terminal Bench 2.0, so is GPT-5.2 Pro (twitter.com)

1 pts|2 months ago|1 comment

Claude Skills as a Meta Tool (leehanchung.github.io)

2 pts|3 months ago|discuss