Swebench - DEV Community

Skip to content

DEV Community

👋 Sign in for the ability to sort posts by relevant, latest, or top.

frontendfacile.it

Aug 3

Perché i benchmark AI stanno diventando inaffidabili (e cosa possiamo imparare da questa crisi)

#benchmarkai #rewardhacking #datacontamination #swebench

5 min read

Jul 31

My context selector beat grep. An agent with grep beat it.

#contextengineering #retrieval #swebench #benchmarking

7 min read

Agentic Drifter

Jul 27

𝗣𝗼𝘀𝘁 𝟯 — 𝗧𝗵𝗲 𝗥𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴 𝗟𝗼𝗼𝗽: 𝗪𝗵𝗲𝗿𝗲 𝘁𝗵𝗲 𝟭.𝟵𝟲% 𝗦𝘁𝗼𝗽𝘀 𝗕𝗲𝗶𝗻𝗴 𝗧𝗵𝗲𝗼𝗿𝘆

#llm #python #machinelearning #swebench

1 min read

Agentic Drifter

Jul 24

𝗣𝗼𝘀𝘁 𝟮 — 𝗪𝗵𝘆 𝗠𝗲𝗱𝗶𝘂𝗺 𝗜𝘀𝘀𝘂𝗲𝘀 𝗠𝗮𝘁𝘁𝗲𝗿 (finding medium software engineering issues, within a #codebase)

#llm #python #machinelearning #swebench

1 min read

Agentic Drifter

Jul 22

Post 1 — SWE‑Bench Reliability Series

#llm #python #machinelearning #swebench

1 min read

Agentic Drifter

Jul 22

Small Model SWE‑bench: What Happens When You Push Tiny Models Into Full Task Pipelines

#llm #swebench #python #machinelearning

2 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.