Tag
Cognee
2 issues found
Sep 29, 2026
The Harness Beats The Model
Description
- Harness Over Model Reliability lives in context, tools, retries and verification — an unmanaged agent reportedly lost 78.7% of SWE-Bench tasks to context overflow.
- Benchmark Blowback Anthropic's Sonnet 5.5 Terminal-Bench "win" over Opus 5.5 compares mismatched effort settings; vendor-reported numbers carry caveats.
- Quotas & Cost OpenAI's Sol 6 rebrand arrives with halved usage, while cost-per-completed-task diverges from list price.
Tags
AlgogentAnthropicArize PhoenixBraintrustCitrixCloudflare+64 more
303 time saved1747 sources52 min read
Sep 14, 2026
Agent Runtimes Beat Model Choice
Description
- Runtime Over Model LangGraph's 6.17M monthly downloads and AA Index v4.3's 45% private-task weighting show selection shifting to harness and evals.
- Code Beats JSON smolagents reports ~30% fewer steps and ~23% higher success; CodeAct cites up to 20% gains.
- Authorization Moves Out Agent-Safe Pipeline, Astrid, and auth.md push auth outside the model; Cloudflare flags third and fourth-party SaaS as the blind spot.
Tags
AMDASMLAWSAlibabaAnthropicArtificial Analysis+95 more
141 time saved1656 sources48 min read