Felix Becker retweetledi
Felix Becker
3.3K posts
Felix Becker
@felixfbecker
I work on making your developer experience with the Claude Platform a joy. Ex Sourcegraph. All opinions are my own.
San Francisco Katılım Nisan 2013
645 Takip Edilen820 Takipçiler
We’re ready for you, SF 🧡
There’s so much exciting stuff to talk about.
English
@PaulUheet We rolled out a fix, let me know if you're still seeing problems!
English
@felixfbecker @felixfbecker any updates on that? still no feedback on the issue...
English
Working on this was a labor of love.
A big part of Claude Managed Agents is stellar developer experience. Our goal was to ship a platform that is incredibly powerful and flexible, but also simple and a joy to use.
We abstract away the hard infra parts, while also giving you the observability you need in Console to be able to debug when things go wrong, improve, iterate.
We iterated over months on API shapes and the SDKs (in 7 languages!) to make them intuitive to devs and Claude.
We made sure Claude Code knows Managed Agents out of the box, so you can ask Claude to write your agents for you, or be your oncall engineer to debug issues.
We colaunched the ant CLI to give you a production-ready way to version-control your agents declaratively along your source code.
We invested in detailed documentation that guides you through best practices.
Whatever agent you want to build, the Claude Platform is here for you!
Claude@claudeai
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.
English
@PaulUheet forwarded this to our billing team, they're looking into it! thank you for reporting!
English
@felixfbecker Could you please take a look at this issue so we in Europe also can use it 🥺 x.com/pauluheet/stat…
Paul Uheet@PaulUheet
@bcherny @trq212 in Europe we cannot use API billing in Claude Platform because of credit card auth issue. Please help! GitHub issue: github.com/anthropics/cla…
English
Felix Becker retweetledi
stable & intuitive APIs should be a priority, not an afterthought. we went back & redesigned earlier Managed Agents API shapes when we saw Claude and our coworkers were struggling to figure out how the various primitives work together.
care for craft should not go away in the era of AI. it's more important than ever.
Jess Yan@jess__yan
A lot of people ask why API taste still matters when agents are writing code. But watching the reaction to Claude Managed Agents is incredibly validating that shapes still fundamentally matter. CMA was designed with human/agent collaboration in mind and it shows.
English
Felix Becker retweetledi
SF dudes say taste is important and then go line up for Salt n Straw in Hayes instead of going to hometown creamery
English
@paularambles pls apply to our marketing team anthropic.com/careers/jobs?t…
English
Felix Becker retweetledi
@HKydlicek We respect robots.txt and other industry standard ways websites may express their preference not to get crawled
privacy.claude.com/en/articles/88…
English
Anthropic brothers, as much as I love your models; you have distillied the whole internet, wikipedia and shit-tons of books.
Distilling your models is only fair game.... Are your scrappers not using residental proxies and respecting robots.txt or are they "malicious" ?
Anthropic@AnthropicAI
We’ve identified industrial-scale distillation attacks on our models by DeepSeek, Moonshot AI, and MiniMax. These labs created over 24,000 fraudulent accounts and generated over 16 million exchanges with Claude, extracting its capabilities to train and improve their own models.
English
Something really clicked for me in the past month using prerelease Opus 4.6 in Fast Mode. Claude just rips through tasks and never gets stuck.
*I'm* actually the bottleneck now.
It's expensive but speed makes a huge difference. I'm so glad we can have more people try it out
Claude@claudeai
Our teams have been building with a 2.5x-faster version of Claude Opus 4.6. We’re now making it available as an early experiment via Claude Code and our API.
English
@anthonyronning @sqs @AmpCode Curious, would you trust it if the threads were stored through stateful APIs offered by the model provider instead?
English
English
See this is my main problem with @AmpCode
It’s a proprietary non-optional data collection nightmare with ads, and you can’t bring your own inference key.
As cool as their team and approach is, I’ll never use it and will never need to. Plenty of competitors that are great.
English
@lisabdunlap @AnthropicAI What's the URL of the first screenshot? Will fix
English
@LeaVerou Aren't HTML attributes case-insensitive though? Meaning anyone is free to write them in camelCase if they want instead of lowercase. As a component author, we don't have to make a choice for the consumer.
English
#webcomponents API design dilemma: consistency with the platform vs ergonomics, pick one, you can't have both.
HTML uses concatenatedcase for attributes¹ which is *terrible* for readability². But if you choose to do something different in your components they will end up with a mix of both since native attributes still apply, which also sucks.
What to do?
¹ #casing-rules" target="_blank" rel="nofollow noopener">w3.org/TR/design-prin…
² Especially as we start having 4 word attributes like shadowrootreferencetarget 🤮
English
We've added tool use support to the Workbench in the Anthropic Console so you can now test prompts that use tools.
English
Felix Becker retweetledi
Prompt engineering is hard. That's why we've been adding tons of features to the Anthropic Console to make the entire process easier for devs.
Our goal is to cut the time you spend working on prompts by >90%.
Here's a quick walkthrough:
English
Felix Becker retweetledi
Extremely excited for this release — the first one I made some humble contributions to 😊
You can try the new Sonnet and compare responses in the Anthropic workbench!
Anthropic@AnthropicAI
Introducing an upgraded Claude 3.5 Sonnet, and a new model, Claude 3.5 Haiku. We’re also introducing a new capability in beta: computer use. Developers can now direct Claude to use computers the way people do—by looking at a screen, moving a cursor, clicking, and typing text.
English