Excited to release Opus 4.8 today! We heard your feedback on 4.7 and have made many fixes for 4.8. 4.8 understands nuances better, feels much more natural to talk to, and is overall a stronger collaborator on everything from coding to knowledge work.
LLMS
-
New Claude features: fast mode, dynamic workflows, effort controls
By
–
Also shipping today:
• Fast mode for Opus 4.8 – 2.5x faster, 3x cheaper vs 4.7
• Dynamic workflows in CC – hundreds of parallel subagents in one session, and verifies its own work • Effort controls on http://
claude.ai – choose how much effort Claude puts into a query -
Behavior change in AI: plans, recovers errors, creative, feels senior
By
–
Benchmarks are great, but IMO the behavior change is a much bigger deal. Plans before it edits, recovers from its own errors, and finds creative ways around obstacles instead of stalling. Feels much more like a senior engineer than 4.7, and better at long-horizon work.
-
Claude Opus 4.8 achieves 69.2% on SWE Bench Pro, beating Opus 4.7
By
–
ANTHROPIC : Claude Opus 4.8 achieves 69.2% score on SWE Bench Pro against 64.3% for Opus 4.7. Benchmarks
-
Opus 4.8: our smartest model, best for coding and agents.
By
–
Opus 4.8 is here! It's our smartest Opus model to date, and the best GA model for coding and agents.
-
New LangChain Academy Course on Scaling Deep Agent Deployment
By
–
New LangChain Academy Course: Intro to LangSmith Deployment
— LangChain (@LangChain) 28 mai 2026
In this course, you’ll learn how to scale a single-user desktop Deep Agent all the way to a multi-tenant deployment running on managed, elastic infrastructure. pic.twitter.com/pFXZRhTZDHNew LangChain Academy Course: Intro to LangSmith Deployment In this course, you’ll learn how to scale a single-user desktop Deep Agent all the way to a multi-tenant deployment running on managed, elastic infrastructure.
-
AI Agents Need to Learn from Executions, Not Just Complexity
By
–
Exacto. Ese es el problema que nadie estaba atacando. Todos haciendo agentes más complejos pero ninguno que realmente aprenda de sus propias ejecuciones
-
Integrating MagicPath AI Agent Skill with Cursor for Code Automation
By
–
For Cursor to communicate with MagicPath, it needs our agent skill. Just paste this inside the Cursor chat. "Install this skill npx skills add https://
github.com/magicpathai/ag
ent-skills
… –skill magicpath" The agent will walk you through the installation, logging into our app and the CLI. If you -
AI Agents Need to Learn from Executions for Meaningful Functionality
By
–
I've been waiting for something like this for a while. Agents that don't learn from their executions make no sense.
-
Systematic failures in long agent runs: repetition, forgetting, high API bill
By
–
You have probably seen this with Claude Code or any long agent run: – it repeats work
– it forgets a decision
– it argues with stale instructions
– it misses the exact file you mentioned earlier
– the API bill keeps climbing That is not random.