come say hi at Code With Claude tomorrow!
ill be giving a talk w @jess__yan on some new things we’re excited to share.
join the livestream here:
claude.com/code-with-clau…
English
Lance Martin
1.2K posts
Lance Martin
@RLanceMartin
staff @anthropicai
San Francisco, CA Katılım Mayıs 2009
432 Takip Edilen29.2K Takipçiler
Lance Martin retweetledi
Claude Code ships with a built-in skill for working with the Claude Platform.
Useful for model migrations, using API features (e.g., prompt caching), or onboarding to newer APIs like Claude Managed Agents.
English
a few lessons we’ve learned on context management + long-term memory
Lance Martin@RLanceMartin
English
across model generations, Claude gets better at using the filesystem to manage memory. i wrote abt one example here from Claude Plays Pokémon (c/o @DavidSHershey): Sonnet 3.5 v Opus 4.6 shows a striking difference in its memory files.
claude.com/blog/harnessin…
English
Claude Managed Agents just added memory. memory files are managed by Claude, shared across sessions, and easily exported / edited.
platform.claude.com/docs/en/manage…
ClaudeDevs@ClaudeDevs
Memory on Claude Managed Agents is now in public beta on the Claude Platform, letting agents learn and improve across different sessions.
English
Lance Martin retweetledi
Memory on Claude Managed Agents is now in public beta on the Claude Platform, letting agents learn and improve across different sessions.
English
Lance Martin retweetledi
Lance Martin retweetledi
Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found.
All are fixed in v2.1.116+ and we’ve reset usage limits for all subscribers.
English
Lance Martin retweetledi
New blog: Building agents that reach production systems with MCP.
When should agents use direct APIs vs CLIs vs MCP? Plus patterns for building MCP servers, context-efficient clients and pairing MCP with skills.
claude.com/blog/building-…
English
@simonw that’s right. you can configure effort in the API. you can also use our skill (built into Claude Code) to do it (or ask it questions about setting effort / other API features).
Lance Martin@RLanceMartin
useful Claude Code tip: if you want to test your code w/ Opus 4.7, just say "migrate to Opus 4.7". the latest release will use our claude-api skill to update model names, prompts, effort, etc specifically for Opus 4.7.
English
OK, here's a resolution - I managed to get it to think using these settings:
"thinking": {
"type": "adaptive", "display": "summarized"
},
"output_config": {
"effort": "max"
}
Without "display": "summarized" I couldn't tell if it thought or not
x.com/simonw/status/…
Simon Willison@simonw
@137ry gist.github.com/simonw/0f1a370… seemed to work - the problem is it no longer reports "reasoning" tokens as a separate line item from output tokens so I couldn't tell if reasoning had happened or not until I turned on the reasoning summary
English
Claude Opus 4.7 with adaptive thinking via the API... am I missing something or is it not possible any more to force it to think?
(Prompt hacks like "think step by step" don't count here, I mean the equivalent of budget_tokens or effort: high in previous Claude models)
English
@MRA_AU @ClaudeDevs if you are using the messages API, you need to configure prompt caching:
platform.claude.com/docs/en/build-…
if you are using Claude Managed Agents API, we handle prompt caching for you:
platform.claude.com/docs/en/manage…
English
@ClaudeDevs Not trying to be rude but isn’t this your job to make sure sessions are cached and same with establishments using your proprietary software?
I don’t mind visual tools, I’m just a bit confused
English
Lance Martin retweetledi
Caching is critical for customers to lower both costs and TTFT.
We’re launching a new dashboard in Claude Developer Console to increase visibility and help customers optimize their usage.
Check it out here: platform.claude.com/usage/cache
English
@trq212 and check it out in the Console here:
platform.claude.com/usage/cache
English
... for some useful tips to improve prompt cache hit rate, check out my blog below and also @trq212 article. also you can just run "/claude-api" in Claude Code to trigger our skill: it can help you configure prompt caching.
claude.com/blog/harnessin…
x.com/trq212/status/…
Thariq@trq212
English
i really like the new prompt caching dashboard in Claude Console. prompt caching is impt for saving cost + improving latency. this dashboard provides very useful diagnostics + visibility.
English
Lance Martin retweetledi
meet claude design! A simple tool that lets designers prototype and share interactive artifacts built using code.
English
Lance Martin retweetledi
A lot of bugs that folks may have hit yesterday when first trying Opus 4.7 are now fixed. Thanks for bearing with us🙏
Ethan Mollick@emollick
I'll give Anthropic credit for moving quickly. Opus 4.7 Adaptive Thinking now triggers thinking much more often, including for the tasks it failed at yesterday. That also means it is doing a lot more web search. So far, a large improvement in output quality on non-coding tasks.
English
@benji_r3 @ClaudeDevs i'll improve some of the wording / guidance here to make it more clear!
English
To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support.
Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.
English