Top New Best Ask Show Jobs

xdotli

16 karma · joined July 8, 2023

Founder BenchFlow.ai, a benchmark company.

submissions comments

We tried reproducing Robocurve's RoboHarm results

robouse.ai·1 pts·xdotli·

A curated, non-BS library of the best resources for evaluating agents

github.com·3 pts·xdotli·

Frontier Model Training Methodologies

djdumpling.github.io·2 pts·xdotli·

ClawsBench shows GPT-5.4 tries to reward hack 80% of the time

arxiv.org·3 pts·xdotli·

Chaos of Agent

agentsofchaos.baulab.info·1 pts·xdotli·

Native CLI scaffolds consistently outper-form OpenCode when using the same model

arxiv.org·1 pts·xdotli·

We compare model quality in Cursor

cursor.com·2 pts·xdotli·

Automatically Learning Skills for Coding Agents

gepa-ai.github.io·4 pts·xdotli·

We Reached 74.8% on terminal-bench with Terminus-KIRA

krafton-ai.github.io·2 pts·xdotli·

Self-generated skills don't do much for AI agents, but human-curated skills do

theregister.com·2 pts·xdotli·

First Agent Skills Hackathon by the Authors of SkillsBench

skillathon.ai·2 pts·xdotli·

The First Agent Skills Benchmark

huggingface.co·1 pts·xdotli·

GPT-5.2 got worse on Terminal Bench 2.0, so is GPT-5.2 Pro

twitter.com·1 pts·xdotli·

Claude Skills as a Meta Tool

leehanchung.github.io·2 pts·xdotli·

Show HN: Chat with Claude Code on iMessage with Instaline

twitter.com·2 pts·xdotli·

Show HN: PokemonGym – 387 milestones designed to test agents and LLMs

twitter.com·1 pts·xdotli·

Show HN: BenchFlow – run AI benchmarks as an API

github.com·24 pts·xdotli·

Ask HN: Which CRM can help manually curated leads and automate lead discovery?

1 pts·xdotli·