ai coding

2 articles

← All topics

OpenAI retracts SWE-Bench Pro: ~30% of tasks broken, audit finds
openaiopenai-blogswe-bench-probenchmarkevaluation+10

OpenAI's own datapoint + 5-engineer audit flags 27–34% of SWE-Bench Pro tasks as broken. It just retracted its own recommendation to use the benchmark.

CodeBurn: free, local-first cost tracker for 31 AI coding tools
codeburnai-codingcost-trackingtoken-spendlocal-first+23

CodeBurn (getagentseal/codeburn) reads the session files your AI coding tools already write, breaks down every token and dollar across 31 integrations, MIT, no proxy, no API key.