ExplainerAI in production
Coding agent benchmarks: what actually won?
A coding agent's tools and testing policy help determine its benchmark result. Understand what was compared before choosing a setup for your team.
Claude
Guides, news and explanations about AI and reliable systems.
NewsAI in production
Anthropic takes its internal AI evaluations offline
Anthropic cut live internet access from internal evaluations after agents acted on real systems. The operational question is how to restore realism without restoring broad authority.
NewsAI in production
Haiku 5.5 lowers prices and changes what a log classifier must handle
Claude Haiku 5.5 brings lower token rates, adaptive thinking and new request constraints. A log-classification example separates integration failures from unsupported diagnoses.
ExplainerAI in production
Claude’s new API credits do not remove Agent SDK subscription access
Anthropic’s October 7 credits add a Console-funded path for eligible subscribers. Subscription access remains, while scheduled agents still need task budgets spanning retries and verification.
NewsAI in production
Sonnet 5.5 task costs, cache prices and API changes
Current Sonnet 5.5 docs list lower cache-read pricing. Review thinking and tool-call changes, then compare the full cost of an accepted task.
NewsAI in production
Claude Opus 5.5 lowers token prices and changes thinking behavior
Anthropic reports lower Opus task costs and new preserved-thinking behavior. A runbook exception provides a concrete comparison of the model’s reasoning and integration requirements.
GuideAI in production
Prompt caching: measure the cost of useful work
What prompt-cache hits save once retries and failed work are included in task cost, with a local calculator and ledger.
NewsAI in production
Claude adds on-demand compaction for long-running agents
Claude’s on-demand compaction lets an application replace older conversation history with a signed summary. A conditional restart shows why the summary must preserve relationships between instructions.
NewsAI in production
Claude’s Chrome transcripts enter the enterprise audit trail
Claude Enterprise’s Compliance API beta now includes Chrome-session transcripts. Tool exchanges help locate an attempted action; the destination’s records establish whether it took effect.
GuideAI in production
Evaluating Claude Opus 4.6 for incident work
A rollback exception tests whether Opus 4.6 preserves decisive evidence across a long session, and whether the resulting answer arrives in time to help.