OpenAIAnthropicGooglexAIPerplexity
← Back to all updatesPublished ·Anthropic• Minor
Anthropic launched the advisor tool in public beta for pairing executor and advisor models mid-generation.
The read
Long-horizon agentic workloads can keep bulk token generation at executor-model rates while getting strategic guidance mid-generation.
The frame
For agentic workloads, model choice now has two roles: executor-token generation and advisor-model guidance.
Primary source
Anthropic →Keep reading
See what Nova3 builds →Related updates
- Jun 12, 2026Anthropic publicly documented stop_details on refusal responses, with category and explanation fields for routing.
- Jun 12, 2026Claude Opus 4.8 defaults the effort parameter to high across all surfaces.
- Jun 12, 2026Claude Opus 4.8 lowers prompt caching’s minimum cacheable prompt length to 1,024 tokens versus Opus 4.7.
This is the world we build in. It moves this fast. We move with it.
Bring us your project →