Anthropic launches Opus 5.5 at 40% lower cost; new workflow mines your coding session history
blaizedsouza · x · 2026-09-23
Anthropic has released Opus 5.5, the first model in its Claude 5.5 family, claiming performance on par with Claude Fable 5.1 for most tasks at 40% lower running cost than Opus 5.
Alongside the launch, @shannholmberg shared a practical workflow for putting the new model to work on your own projects:
- Feed it project files plus session history: have the agent locate all local sessions from Claude Code, Codex, or other tools, and read them alongside current files, instructions, and plans — in batches if the history is large, saving findings as it goes.
- Ask it to review how you work: sessions contain your corrections, failed attempts, and decisions that never made it into project docs. Look for repeated instructions, manual tasks, missing context that causes mistakes, failed approaches, and unfinished work — with citations back to the underlying sessions.
- Verify findings against the original records to guard against hallucination.
More from coding & agent
- Google's MCP Apps extension lets MCP servers return interactive UI components — rseroter · 2026-09-23
- Dev runs 32 coding agents burning 5-10B tokens a day in Zed — generativist · 2026-09-23
- Stanford paper: self-organizing agent team hits 66.7%, beats best single model's 48.8% — dair_ai · 2026-09-23
- Google's ToolGrad reverses tool-use data generation, hits 83.1 BFCL with 12B Gemma-3 — dl_weekly · 2026-09-23
- Using AI agents to book things still costs as much mental effort as doing it yourself — nabeelqu · 2026-09-23
- LangChain to unveil new products Thursday, previewed live at Interrupt keynote — LangChain · 2026-09-23