Lydia Hallie ✨ (@lydiahallie) header
Lydia Hallie ✨ (@lydiahallie) profile picture

Lydia Hallie ✨

@lydiahallie

Claude Code @AnthropicAI @ClaudeDevs

 San Francisco, CA
Joined June 2017
  • Tweets1.5K
  • Following43
  • Followers177K
127Media
Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)Photo by Lydia Hallie ✨ (@lydiahallie)
Lydia Hallie ✨ retweeted
Adam Wolff (@dmwlff) profile picture
Adam Wolff
@dmwlffOct 29
ultrathink is back in the CC CLI. We turned this off for a while because it's weird and maybe confusing. But I like weird, and I don't think it's that confusing. I mostly run Opus 5.5 on medium. Some turns, though, I want to put a little extra mustard on it. ultrathink!
121
60
38
1,886
142,899
Dynamic workflows don't have to be hundreds of subagents btw! I use them for any task I want to rerun the same way, even just ~10 subagents It's a JavaScript file you can edit, so you have full control over the subagents and the order they run in. More predictable than a skill!
104
49
9
1,426
87,915
You don't have to import anything either, agent()/pipeline()/parallel() etc are just globals in the script! Ask Claude to "make a workflow that does X" and it'll write the file, then you can save it from /workflows and rerun it as /name
7
2
77
9,061
We're reworking the UI and setup flow for plugins and connectors in Claude. How can we make it better for you? All feedback welcome 🙏
464
21
8
1,763
119,976
Lydia Hallie ✨ retweeted
Daisy Hollman (@The_Whole_Daisy) profile picture
Daisy Hollman
@The_Whole_DaisyOct 26
Fun fact: `--dangerously-skip-permissions` doesn't actually approve EVERYTHING—we still block some obvious things like `rm -rf ~`. But today's release will let you disable this if you really want, by setting a new env var `CLAUDE_CODE_EVEN_MORE_DANGEROUSLY_SKIP_PERMISSIONS=1`
202
141
114
3,922
568,196
Lydia Hallie ✨ retweeted
Meaghan (@meaghaneschoi) profile picture
Meaghan@meaghaneschoiOct 23
ICYMI the Claude Desktop app just got a facelift. With a new set of icons, a simplified type system and a ton more details that create a UI more focused on your work with Claude. @aaandeverything @khalilcader @daniel__designs +jmr for sweating the details
Image from Meaghan (@meaghaneschoi)
136
23
24
1,141
142,903
Quick reminder that the free limit reset from last month expires tomorrow at 9am PT! 🙏 If you haven't used yours yet, it's still waiting for you in Settings > Usage (or clau.de/reset)
Image from Lydia Hallie ✨ (@lydiahallie)
389
102
62
2,614
263,829
Claude Duet has made focused work so much easier! Not having to be "on" all the time is so nice, way less context switching My setup is boring lol but I have it watch Slack/email/cal and only ping me when it matters (even threads I'm not in), often with a doc/design for context!
Claude (@claudeai) profile pictureClaude
@claudeaiOct 21
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
118
35
3
1,100
107,758
We’ve been working with OpenCode on yesterday’s breach and have revoked Claude API keys we believe were affected. If you saved a key in OpenCode and want to be extra careful, please create a new one!
OpenCode (@opencode) profile pictureOpenCode
@opencodeOct 17
We had a security breach last night related to a large scale distillation attack that impacted 1.4% of OpenCode Console users We have notified them all this morning via email. If you did not get an email you were not impacted, it was a subset of users who had external providers linked The incident is ongoing so we cannot share more details at this point but we are working with Anthropic, OpenAI, and Google to remediate
74
53
28
1,525
128,383
We recently added idle compaction to Claude Code! It now compacts long idle sessions right before the prompt cache expires (~1h). If you come back to it later, it only has to reprocess the summary instead of the entire conversation, which saves you some usage.
Image from Lydia Hallie ✨ (@lydiahallie)
513
196
157
6,318
259,775
It does mean that Claude continues from a summary instead of your full context though. You can turn it off with "idleCompaction": false in settings.json, and you can set a custom threshold (default is 200k) with CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS
49
14
7
403
38,863
So many great updates to the Claude desktop app, def give it a try if you haven't used it in a while (or if you're mainly on the CLI!)
ClaudeDevs (@ClaudeDevs) profile pictureClaudeDevs
@ClaudeDevsOct 14
We've been working hard on making the Claude Code desktop app great for running lots of sessions side by side. It's now much quicker to start sessions, easier to split work across a few, and you can always see what each of them is doing. Here’s what's new:
166
23
3
1,370
76,334
Just to avoid some confusion: auto-compact does summarize. When it runs, your whole conversation is replaced by a short summary. It doesn't keep the last 1M tokens around. The ~967K is only when it runs on 1M models. Compacting itself is just one request that reads about as many tokens as the message you sent right before it, and it's mostly cache reads if your cache is still warm. What @rohit3a found is that waiting until 967K means every message before that point uses a lot of tokens, because each one includes your whole conversation so far. Most of it is read from the cache, which is much cheaper (so this is usually fine as long as your cache is warm), but it still counts toward your usage and adds up as your conversation grows. /autocompact 400k makes it summarize at 400K instead, so your messages never get that big.
Lxyv (@wholyv) profile pictureLxyv
@wholyvOct 9
holy fuck. so auto compact basically loads last 1M tokens into context by default on claude? and here i thought they were summarising and reducing the context loads. no wonder people used to burn anywhere from 2%-15% 5h limits simply for auto compacting their sessions.
213
118
61
3,166
606,974
Everyone on the Projects waitlist who's on Pro/Max should have access now 🎉 Would love to hear your feedback!
ClaudeDevs (@ClaudeDevs) profile pictureClaudeDevs
@ClaudeDevsOct 9
We just let in every Pro and Max user from the Claude Code Projects waitlist! If you're new to Claude Code Projects, here's a 4 minute walkthrough to get you started:
139
24
6
963
80,070
Lydia Hallie ✨ retweeted
Claude (@claudeai) profile picture
Claude
@claudeaiOct 7
One more thing: we’re halving the price of cache reads on Claude Sonnet 5.5, to $0.10 per million tokens. That makes Sonnet 5.5 around 20% cheaper to run on most long-running work.
218
586
394
11,843
1,582,220
If you're on API billing, you can set Haiku 5.5's autocompact window to 100K so you stay in the cheaper token pricing tier! It's saved per model so this only applies to Haiku (incl. subagents) > /model haiku > /autocompact 100k
ClaudeDevs (@ClaudeDevs) profile pictureClaudeDevs
@ClaudeDevsOct 7
Replying to @ClaudeDevs
For prompts under 100K tokens, it's $0.10 / $0.50 per million tokens with cache reads at $0.01. Above 100K tokens, $0.50 / $2.50 per million, with cache reads at $0.05.
106
80
18
2,349
164,952
hi haiku 🥹 such a great model for tasks that are mostly reading/small edits/tool calls and don't need much reasoning!
Claude (@claudeai) profile pictureClaude
@claudeaiOct 7
Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.
89
23
4
1,068
39,769
You can now ask Claude to run subagents at a specific effort level! Make sure you're on v2.1.292+
Image from Lydia Hallie ✨ (@lydiahallie)
208
149
55
3,091
125,808
desktop support coming very soon!
11
125
13,735
You can still claim your one-time bonus credit for cloud sessions until Oct 7! Run /claim-credit
ClaudeDevs (@ClaudeDevs) profile pictureClaudeDevs
@ClaudeDevsOct 6
Cloud sessions run Claude Code on a fresh VM for each task, so you can start several at once and they keep going when you close your laptop. We wrote a field guide with seven workflows that suit them, plus how to connect GitHub on the first try. claude.dev/blog/claude-code-…
Claude Code in the cloud: a field guide to cloud sessions / claude.dev Blog

Claude Code in the cloud: a field guide to cloud sessions / claude.dev Blog

Cloud sessions run Claude Code on a fresh VM for each task. Four real sessions, seven workflows that suit them, and how to connect GitHub without getting stuck.

claude.dev
69
17
4
613
67,783
Load more