Artifacts just got an upgrade!
ClaudeDevs@ClaudeDevs
Artifacts now support public sharing and multiplayer editing in Claude Code, and can be created with Claude Tag.
English
cat
1.5K posts
cat
@_catwu
claude code + cowork @anthropicai, prev: @dagster, @scale_ai
sf Katılım Mart 2018
352 Takip Edilen95.3K Takipçiler
Claude Code can now open any website inside the desktop app.
Claude can use your production app, open the links it sends you, check Twitter, and even watch the FIFA World Cup!
ClaudeDevs@ClaudeDevs
Claude Code on desktop now has an in-app browser. Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers. It's sandboxed and configurable: you choose whether sessions persist.
English
cat retweetledi
We've reset 5-hour and weekly rate limits for all users.
English
Tomorrow at 10am PT I'm hosting a live walkthrough of how we progressed from single-player Claude Code to multi-player Claude Tag. Then, we're going deep on how Claude Tag actually works.
AI used to finish your sentence. Then, it wrote entire features. Now, Claude Tag can monitor your channels, do proactive work for you, the whole team can steer it, and it remembers what you told it last week.
Register: anthropic.com/webinars/how-a…
English
We've put together a short history of how Claude Code came to be, told by the people who built it and the early users who helped make it what it is today.
anthropic.com/features/makin…
English
@DavidSHolz when i use claude tag, i ask it to write regular summaries of all running agents, kind of like a chief of staff. and i’ve been asking it to change the format of the reports to make it higher information density / more actionable
English
@DavidSHolz i like focused work on a hard task with a single agent so i can quickly correct it when i notice bad assumptions and keep track of its progress. usually i run 10s of agents, but it’s nice to get into the zone and in the weeds of one task to get it done well
English
my friends are all feeling extremely productive and also extremely drained with the latest coding models. this makes me feel like something is wrong, and also that there might be a big opportunity. does anyone have any strategies they use to make it feel better day-to-day?
English
i write a prompt with the role and output requirements, then ask claude code in natural language to use dynamic workflows. this feature lets cc orchestrate hundreds of agents map-reduce style: it spins them all up in parallel, each researching one candidate, then merges everything into a single list and emails it to me when it’s done. you can inspect the workflow json it generates, but i usually don’t unless something goes wrong
English
what are your top claude code + workflows + artifacts use cases?
one of my new favorites is for sourcing candidates:
- tell cc about the role and backgrounds i’m looking for
- ask cc to kick off a dynamic workflow to find 100 candidates, and include linkedin, twitter, blog, podcasts, and one-line pitch for each
- ask cc to make an artifact and email it to me. then, i lock my laptop and head out for the day
- i review the list on the go once cc is done!
English
@_catwu @The_Whole_Daisy Here is what Fable drew, just for you
Fable: "i like to draw home." Because that's what Claude Code is to me
Fable says "hi, and thank you for the house"
English
What are you building with Fable 5 this long weekend? Show me your demos in the replies!
Claude@claudeai
Fable 5 is back.
English
@_catwu I use artifacts when investigating alternatives, helps me visualize the pros/cons to make a decision + it is a nice visual I can show to non-devs.
Though I usually gather info beforehand in a normal session, workflows eat up my 5h window too fast
English
@danmana @The_Whole_Daisy this is so cool! would love to see what fable likes to draw
English
@The_Whole_Daisy @_catwu Thanks, I had lots of fun letting Claude print whatever it likes
English
@_catwu How weak is Fable 5 2.0 vs. OG Fable 5?
Anecdotally it feels significantly less capable but I’m just one test case…
English
One of the things I love about Claude Fable 5 is that it knew to use propensity score matching (matching users on activity so you compare like with like) in my retention analysis without me asking.
It’s exciting to see Fable 5’s improved judgment across all of its work, from writing emails and docs in Cowork to debugging complex errors in Claude Code
English