# \#claude **URL:** https://forum.devtalk.com/tag/claude/3244.md [Latest](https://forum.devtalk.com/latest.md) · [Categories](https://forum.devtalk.com/categories.md) · [Tags](https://forum.devtalk.com/tags.md) --- ## [How the Claude Code team does code review / claude.dev Blog](https://forum.devtalk.com/t/how-the-claude-code-team-does-code-review-claude-dev-blog/250843)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [19 October 2026 10:19 UTC](https://forum.devtalk.com/t/how-the-claude-code-team-does-code-review-claude-dev-blog/250843 "2026-10-19T10:19:00Z")
How do you review code at the volume agents produce it? On the Claude Code team, once we had high coverage and deep reviews, we started optimizing for the minimum amount of human review time that doesn’t raise reverts o… --- ## [Claude at Work (Manning)](https://forum.devtalk.com/t/claude-at-work-manning/250503)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [8 October 2026 11:01 UTC](https://forum.devtalk.com/t/claude-at-work-manning/250503 "2026-10-08T11:01:43Z")
The Claude suite of LLM-powered tools and agents from Anthropic has radiacally–and permanently–changed the way technical professionals design and create software. From agentic code generation to assistants that capture … --- ## [Getting the most out of Opus 5.5 in Claude and Claude Code / claude.dev Blog](https://forum.devtalk.com/t/getting-the-most-out-of-opus-5-5-in-claude-and-claude-code-claude-dev-blog/250337)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [6 October 2026 10:32 UTC](https://forum.devtalk.com/t/getting-the-most-out-of-opus-5-5-in-claude-and-claude-code-claude-dev-blog/250337 "2026-10-06T10:32:25Z")
How to prompt Opus 5.5, steer a long run, and check your results in Claude apps and Claude Code. Read in full here: --- ## [Ungate - use Claude Pro and ChatGPT Plus in Cursor without API tokens](https://forum.devtalk.com/t/ungate-use-claude-pro-and-chatgpt-plus-in-cursor-without-api-tokens/248917)
**Author:** [@orchidfiles](https://forum.devtalk.com/u/orchidfiles)\ **Replies:** 0\ **Last updated:** [18 August 2026 00:02 UTC](https://forum.devtalk.com/t/ungate-use-claude-pro-and-chatgpt-plus-in-cursor-without-api-tokens/248917 "2026-08-18T00:02:10Z")
If you already have a Claude or ChatGPT subscription, using those models in Cursor usually means paying twice: once for the subscription and once for API tokens. Subscriptions don’t provide an API endpoint, and Cursor ro… --- ## [Introducing Claude Opus 5](https://forum.devtalk.com/t/introducing-claude-opus-5/248266)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [26 July 2026 02:19 UTC](https://forum.devtalk.com/t/introducing-claude-opus-5/248266 "2026-07-26T02:19:18Z")
Opus 5 is a step change improvement for the Opus tier powering long-running agents while delivering improvements in coding and professional work. Read in full here: https://www.anthropic.com/news/claude-opus-5 --- ## [Has anyone seen a model's cost swing 60x on the same task?](https://forum.devtalk.com/t/has-anyone-seen-a-models-cost-swing-60x-on-the-same-task/247229)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 1\ **Last updated:** [12 June 2026 01:34 UTC](https://forum.devtalk.com/t/has-anyone-seen-a-models-cost-swing-60x-on-the-same-task/247229 "2026-06-12T01:34:07Z")
I was reading through a curated list of 60 real-world Claude Fable 5 cases (each logged with input, process, output, and an evidence tag), and one comparison stopped me cold. Same Physarum simulation, two stacks: GPT… --- ## [Claude Code's entire source just leaked (512K lines) - anyone else digging through it?](https://forum.devtalk.com/t/claude-codes-entire-source-just-leaked-512k-lines-anyone-else-digging-through-it/239586)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 5\ **Last updated:** [25 May 2026 18:22 UTC](https://forum.devtalk.com/t/claude-codes-entire-source-just-leaked-512k-lines-anyone-else-digging-through-it/239586 "2026-05-25T18:22:56Z")
Woke up to this today: Claude Code’s complete source code exposed via npm source map. Not a snippet. All 512,000 lines. 1,900 TypeScript files. How it happened Single .map file in production npm package → R2 bucket URL … --- ## [Anyone else running multiple coding agents right now?](https://forum.devtalk.com/t/anyone-else-running-multiple-coding-agents-right-now/244925)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 0\ **Last updated:** [14 May 2026 16:48 UTC](https://forum.devtalk.com/t/anyone-else-running-multiple-coding-agents-right-now/244925 "2026-05-14T16:48:14Z")
Cursor cloud agent development This month’s updates: Codex got real Windows sandboxing (May 13) — dedicated user accounts, OS-level firewall rules Cursor shipped cloud agent de… --- ## [Anyone tried mattpocock/skills for Claude Code? Here is what I found after a week](https://forum.devtalk.com/t/anyone-tried-mattpocock-skills-for-claude-code-here-is-what-i-found-after-a-week/244771)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 0\ **Last updated:** [13 May 2026 16:00 UTC](https://forum.devtalk.com/t/anyone-tried-mattpocock-skills-for-claude-code-here-is-what-i-found-after-a-week/244771 "2026-05-13T16:00:07Z")
Been using the skills repo (77K stars, #1 on GitHub Trending recently) with Claude Code. Sharing what worked and what did not. What worked well: /grill-with-docs — the agent asks detailed questions before coding, the… --- ## [Claude Code, Markdown, and the Case for HTML Artifacts](https://forum.devtalk.com/t/claude-code-markdown-and-the-case-for-html-artifacts/244338)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 0\ **Last updated:** [9 May 2026 15:24 UTC](https://forum.devtalk.com/t/claude-code-markdown-and-the-case-for-html-artifacts/244338 "2026-05-09T15:24:57Z")
Claude Code, Markdown, and the Case for HTML Artifacts I do not think Markdown is going away. It is still the right format for README files, changelogs, API references, and anything that needs clean review in Git. But… --- ## [Anyone else hitting Claude Code rate limits way too fast?](https://forum.devtalk.com/t/anyone-else-hitting-claude-code-rate-limits-way-too-fast/243955)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 0\ **Last updated:** [6 May 2026 15:28 UTC](https://forum.devtalk.com/t/anyone-else-hitting-claude-code-rate-limits-way-too-fast/243955 "2026-05-06T15:28:40Z")
Been using Claude Code on Max for a few weeks and kept running into rate limits by early afternoon. Same tasks as colleagues who weren’t hitting limits at all. Figured it was just quota differences, but it turns out the … --- ## [Why I Cancelled Claude: Token Issues, Declining Quality, and Poor Support](https://forum.devtalk.com/t/why-i-cancelled-claude-token-issues-declining-quality-and-poor-support/242649)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 11\ **Last updated:** [1 May 2026 09:28 UTC](https://forum.devtalk.com/t/why-i-cancelled-claude-token-issues-declining-quality-and-poor-support/242649 "2026-05-01T09:28:48Z")
First enthusiasm A couple of weeks ago I subscribed to Claude Code, and during the first few weeks I had a really nice experience. It was fast, the token allowance was fair, and the quality was good. I learned they had… --- ## [How are you handling the Claude Opus 4.7 migration?](https://forum.devtalk.com/t/how-are-you-handling-the-claude-opus-4-7-migration/243245)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 0\ **Last updated:** [30 April 2026 15:01 UTC](https://forum.devtalk.com/t/how-are-you-handling-the-claude-opus-4-7-migration/243245 "2026-04-30T15:01:59Z")
Anthropic shipped Opus 4.7 last week and the agentic coding improvements look real. But the breaking changes are giving me pause. Specifically: temperature, top\_p, top\_k at non-default values now return 400 Extend… --- ## [Has anyone tried the Karpathy CLAUDE.md rules? (97.8k stars)](https://forum.devtalk.com/t/has-anyone-tried-the-karpathy-claude-md-rules-97-8k-stars/243109)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 1\ **Last updated:** [30 April 2026 01:16 UTC](https://forum.devtalk.com/t/has-anyone-tried-the-karpathy-claude-md-rules-97-8k-stars/243109 "2026-04-30T01:16:04Z")
There’s a GitHub repo at forrestchang/andrej-karpathy-skills that’s sitting at 97.8k stars. It’s a single CLAUDE.md file with four behavioral rules for Claude Code, derived from Andrej Karpathy’s observations about LLM c… --- ## [Should we be worried that an AI model just found bugs that human auditors missed for 27 years?](https://forum.devtalk.com/t/should-we-be-worried-that-an-ai-model-just-found-bugs-that-human-auditors-missed-for-27-years/240559)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 5\ **Last updated:** [21 April 2026 13:49 UTC](https://forum.devtalk.com/t/should-we-be-worried-that-an-ai-model-just-found-bugs-that-human-auditors-missed-for-27-years/240559 "2026-04-21T13:49:23Z")
Anthropic announced Claude Mythos Preview this week – and then said it will not release it to the public. Their reasoning: the model’s cyber capabilities have crossed a threshold where broad access without safeguards is … --- ## [Switching to Claude Code + VSCode inside Docker](https://forum.devtalk.com/t/switching-to-claude-code-vscode-inside-docker/206727)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 2\ **Last updated:** [21 April 2026 12:51 UTC](https://forum.devtalk.com/t/switching-to-claude-code-vscode-inside-docker/206727 "2026-04-21T12:51:23Z")
Why I decided to ditch Cursor and switch to running Claude Code in an isolated environment + diy guide! Read in full here: --- ## [Claude Design - is the "design system inference" feature actually useful in practice?](https://forum.devtalk.com/t/claude-design-is-the-design-system-inference-feature-actually-useful-in-practice/241951)
**Author:** [@xiji2646-netizen](https://forum.devtalk.com/u/xiji2646-netizen)\ **Replies:** 0\ **Last updated:** [20 April 2026 14:29 UTC](https://forum.devtalk.com/t/claude-design-is-the-design-system-inference-feature-actually-useful-in-practice/241951 "2026-04-20T14:29:26Z")
Anthropic launched Claude Design this week and there’s a lot of noise about the generation demos and the stock reaction. But the feature I’m most curious about in practice is design system inference. The claim: during s… --- ## [How I’m Productive with Claude Code](https://forum.devtalk.com/t/how-i-m-productive-with-claude-code/238753)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 1\ **Last updated:** [24 March 2026 14:23 UTC](https://forum.devtalk.com/t/how-i-m-productive-with-claude-code/238753 "2026-03-24T14:23:40Z")
It’s been about 6 weeks since I joined Tano, and this is what my commit history looks like: Read in full here: --- ## [150,000 Lines of Vibe Coded Elixir: The Good, The Bad, and The Ugly](https://forum.devtalk.com/t/150-000-lines-of-vibe-coded-elixir-the-good-the-bad-and-the-ugly/229019)
**Author:** [@John-BoothIQ](https://forum.devtalk.com/u/John-BoothIQ)\ **Replies:** 0\ **Last updated:** [7 January 2026 00:42 UTC](https://forum.devtalk.com/t/150-000-lines-of-vibe-coded-elixir-the-good-the-bad-and-the-ugly/229019 "2026-01-07T00:42:31Z")
TL;DR: Good: AI is great at Elixir. It gets better as your codebase grows. Bad: It defaults to defensive, imperative code. You need to be strict about what good Elixir looks like. Ugly: It can’t debug concurrent… --- ## [Rob Pike (co-creator of Go) on GenAI](https://forum.devtalk.com/t/rob-pike-co-creator-of-go-on-genai/227815)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 5\ **Last updated:** [1 January 2026 22:01 UTC](https://forum.devtalk.com/t/rob-pike-co-creator-of-go-on-genai/227815 "2026-01-01T22:01:26Z")
Fuck you people. Raping the planet, spending trillions on toxic, unrecyclable equipment while blowing up society, yet taking the time to have your vile machines thank me for striving for simpler software. Just fuck you… --- ## [My experience trying to write human-sounding articles using Claude AI](https://forum.devtalk.com/t/my-experience-trying-to-write-human-sounding-articles-using-claude-ai/133377)
**Author:** [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\ **Replies:** 2\ **Last updated:** [1 December 2025 03:40 UTC](https://forum.devtalk.com/t/my-experience-trying-to-write-human-sounding-articles-using-claude-ai/133377 "2025-12-01T03:40:49Z")
My experience trying to write original, full-length human-sounding articles using Claude AI. You can use AI tools like Claude to help you write full-length content. By going paragraph-by-paragraph, you can direct the A… --- ## [Thinking Elixir 279 - Hot Code Upgrades and Hotter AI Takes](https://forum.devtalk.com/t/thinking-elixir-279-hot-code-upgrades-and-hotter-ai-takes/223160)
**Author:** [@brainlid](https://forum.devtalk.com/u/brainlid)\ **Replies:** 1\ **Last updated:** [19 November 2025 09:23 UTC](https://forum.devtalk.com/t/thinking-elixir-279-hot-code-upgrades-and-hotter-ai-takes/223160 "2025-11-19T09:23:28Z")
Episode 279 of Thinking Elixir. News includes Chris McCord’s FlyDeploy for zero-downtime hot code upgrades on Fly.io, the Elixir GRPC library update with interactive Livebook documentation, ErrorTracker v0.7.0 with LiveV… --- ## [The RLHF Book (Manning)](https://forum.devtalk.com/t/the-rlhf-book-manning/223158)
**Author:** [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\ **Replies:** 0\ **Last updated:** [18 November 2025 10:44 UTC](https://forum.devtalk.com/t/the-rlhf-book-manning/223158 "2025-11-18T10:44:21Z")
After ChatGPT used RLHF to become production-ready, this foundational technique exploded in popularity. In The RLHF Book, AI expert Nathan Lambert gives a true industry insider’s perspective on modern RLHF training pipe…