HNHacker News
TopNewBestAskShowJobs

raffisk

11 karma · joined November 12, 2025

Building & breaking things
submissionscomments

Show HN: DFAH-Bench – same agent decision, different tool paths

github.com·1 pts·raffisk·
0

DFAH – open-source harness for replayable tool-using LLM agents

github.com·2 pts·raffisk·
1

LLM Output Drift in Financial Workflows: Validation and Mitigation (arXiv)

arxiv.org·24 pts·raffisk·
26