Top all-time · #3395
claude.dev Blog
Company blog · claude.dev/blogaiprogramming
claude.dev Blog is the company blog at claude.dev, writing about ai and programming. Since 2026, 21 different Hacker News readers have linked it 23 times, most often “Getting the most out of Opus 5.5 in Claude and Claude Code”. It is still writing: the last post was on 2026-10-15, and you can follow it by feed.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
HN commenters link claude.dev posts as Anthropic's published material on code review, Opus 5.5 prompting and context engineering, usually cited as sources or context rather than praised.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Articles, videos, and build logs from Anthropic’s developers on building with Claude and Claude Code, including tips, tricks, and points of view.
Most-linked posts?
- Getting the most out of Opus 5.5 in Claude and Claude Code5 people · 5 mentions · first linked 2026-09-22
- How the Claude Code team does code review5 people · 5 mentions · first linked 2026-10-16
- Automating eval design and hillclimbing with Claude4 people · 4 mentions · first linked 2026-09-29
- Getting started with Claude Code mods2 people · 2 mentions · first linked 2026-10-01
- The new rules of context engineering for Claude 5 generation models2 people · 2 mentions · first linked 2026-10-11
What Hacker News says?
Anthropic recently published their code review approach that supports them deploying 30,000 (!) times a day: https://claude.dev/blog/solving-code-review-at-anthropic/
Comment linking /blog/solving-code-review-at-anthropic/
on “We should be more ambitious with the software we build”Submitted How the Claude Code team does code review as a story · 488 points
HN discussionHow do you know it's "Just Good Enough" to ship? I will repeat: We were complaining about awful software before LLMs. Why is it now absolutely okay to write significantly more shitty software just because it's LLMs? For example, for all the claims of how LLMs are better than humans, or how you can ship gazillion LoC easily, we've yet to see any significant number of actual good software to come out of this slopathon…
Comment linking /blog/solving-code-review-at-anthropic/
on “How the Claude Code team does code review”Submitted Getting the most out of Opus 5.5 in Claude and Claude Code as a story · 252 points
HN discussionBecause it’s in a page accessible from its search tool presumably https://claude.dev/blog/getting-the-most-out-of-opus-5-5/
Comment linking /blog/getting-the-most-out-of-opus-5-5/
on “Once Claude can measure something, it can make it faster”Submitted Once Claude can measure something, it can make it faster as a story · 231 points
HN discussionThis issue is mentioned on the Opus 5.5 post [1] from Anthropic (no idea if it has been added after your rant): > Don’t ask it to show its reasoning in the reply > > What to do. Remove requests to reproduce its internal reasoning in the reply from your prompts and instructions. > > Why it matters on Opus 5.5. A request to reproduce its internal reasoning in the reply can be declined. It’s one of the flag categories.…
Comment linking /blog/getting-the-most-out-of-opus-5-5/
on “Once Claude can measure something, it can make it faster”Submitted Automating eval design and hillclimbing with Claude as a story · 4 points
HN discussionAll that credit goes to Rafi. I believe that he either noticed that they were getting long winded in a code review, or suspected that they needed trimming after reading this blog post from Anthropic: https://claude.dev/blog/the-new-rules-of-context-engineering... . It was definitely human driven, but I believe that the agents did the actual trimming.
Comment linking /blog/the-new-rules-of-context-engineering-for-claude-5-generation-models/
on “Five months treating bugs like patients and coding agents like a medical team”Submitted Getting started with Claude Code mods as a story · 3 points
HN discussion> before sending your stuff to other people for review, you need to make the work reviewable. Yes, but the amount of work needed here is overstated. With good orchestration/prompting in the task[1] (and token budget), the work on this end is significantly reduced. … and then the brain drain issue returns. [1] https://claude.dev/blog/solving-code-review-at-anthropic/
Comment linking /blog/solving-code-review-at-anthropic/
on “The Brain Sandwich”Submitted Automating evals with Claude Code native skill as a story · 3 points
HN discussionSubmitted Using Claude Code: Spending your effort as a story · 3 points
HN discussionSubmitted Getting the most out of Opus 5.5 in Claude and Claude Code as a story · 3 points
HN discussionSubmitted How the Claude Code team does code review as a story · 2 points
HN discussionSubmitted The new rules of context engineering for Claude 5 generation models as a story · 2 points
HN discussionSubmitted Claude Code in the Cloud as a story · 2 points
HN discussionSubmitted Getting started with Claude Code mods as a story · 2 points
HN discussionSubmitted Automating eval design and hillclimbing with Claude as a story · 2 points
HN discussionSubmitted When to choose Sonnet over Opus, what it costs, and how to tune it as a story · 2 points
HN discussionSubmitted Getting the most out of Opus 5.5 in Claude and Claude Code / claude.dev as a story · 2 points
HN discussionSubmitted Automating eval design and hillclimbing with Claude as a story · 1 points
HN discussionSubmitted Claude.dev Blog / technical writing for people building with Claude as a story · 1 points
HN discussion
