OpenAI says it found widespread task issues in SWE-Bench Pro, estimates ~30% of tasks are broken, and retracts its earlier recommendation to adopt the benchmark
Sponsor Posts
Subquadratic: the LLM built for 12M-token reasoning — SubQ can reason across entire codebases and document sets in one pass with no RAG workarounds. Read how SubQ 1.1 Small holds near-perfect retrieval out to 12M tokens.
Stop vibe coding analytics — Equals AI turns questions about your business into auditable spreadsheet models and dashboards. Build once, iterate for years.
From MCP to billing: Updates that accelerate hiring — TL;DRConnect your favorite AI tools to Zoho Recruit with Zoho Recruit MCP.Catch up on conversations faster with Zia email summaries.Review candidate context instantly …
Protecting your Cloud Applications Data — Backing up Office 365, Google Workspace, Dropbox & Salesforce data is critical to preventing data loss or corruption, complying with laws and avoiding critical downtime in case of a disaster.
Featured Podcasts
A podcast mostly about tech. Brought to you weekly...
Copyright of this story solely belongs to techmeme.com. To see the full text click HERE
