Top all-time · #13867
patrickmccanna.net
Personal blog · patrickmccanna.net · on HN as 0o_MrPatrick_o0aiprogramming
patrickmccanna.net is a personal blog at patrickmccanna.net about ai and programming. Since 2025, 5 different Hacker News readers have linked it 19 times, most often “Claude Code's "extended thinking" is a summary- not authentic thinking”. It is still writing: the last post was on 2026-10-27, and you can follow it by feed.
Too few sampled comments (4) to say how often HN recommends it.?
Why HN links it
HN commenters link this blog's posts on the visible text in Claude Code's extended thinking and on limiting Claude Code's file access. The comments cite the posts as sources and do not judge the writing.
Summarised by Claude from a sample of 4 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Claude Code's "extended thinking" is a summary- not authentic thinking3 people · 4 mentions · first linked 2026-06-22
- Bubblewrap: A nimble way to prevent agents from accessing your .env files2 people · 2 mentions · first linked 2026-01-15
What Hacker News says?
The local models are willing to share their thinking. The Big AI models don't share their thinking, leaving only vague summaries. Having an AI that deliberately cloaks it's reasoning, that goes out of it's way to act like a Searls Chinese Room Experiment, that deliberately conceals information is incredibly gross. I love what I get from Opus or GPT, but mainly I use GLM and it's so starkly apparent how much better i…
Comment linking /the-text-in-claude-codes-extended-thinking-output-is-not-authentic/
on “Anthropic updates their terms to verify age or identity”Submitted Notes on gotchas while migrating 35kb preprompts from Opus to self-hosted Ollama as a story · 140 points
HN discussionI think the self-doubt might actually be a very crucial part of it's capability. I often feel compelled to interrupt when I'm watching it think (which thank the stars it let's us do, unlike the big American models!!), but usually it makes the right pick! Being willing and able to reconsider seems very good. Going around and around, pulling in more thinking, integrating it: maybe that's why it is as good as it's good…
Comment linking /the-text-in-claude-codes-extended-thinking-output-is-not-authentic/
on “GLM-5.2 is the step change for open agents”Submitted The Boot Order of the Raspberry Pi Is Unusual as a story · 37 points
HN discussion> They achieve this by reselling capacity from pooled Claude Max accounts, payments fraud, and also reselling the model output & reasoning chains to various Chinese labs. Claude never provides the raw reasoning chain. What you see is just a summary of that reasoning. Getting the full thinking output requires an enterprise agreement. https://patrickmccanna.net/the-text-in-claude-codes-extended...
Comment linking /the-text-in-claude-codes-extended-thinking-output-is-not-authentic/
on “Anthropic Accuses Alibaba of 'Illicitly' Accessing AI Models”Submitted Claude Code's "extended thinking" is a summary- not authentic thinking as a story · 21 points
HN discussionSomeone tried this earlier this year but they ended up going with bubblewrap (what Anthropic uses for the sandbox). Here's the blog if you're interested. https://patrickmccanna.net/a-better-way-to-limit-claude-code... I ended up creating an LXC on my homelab and providing it access there, with a self-hosted gitea server but that's only for side projects that I want to host, not develop actively.
Comment linking /a-better-way-to-limit-claude-code-and-other-coding-agents-access-to-secrets/
on “Don't YOLO your file system”Submitted Prompt Patterns That Compound as a story · 3 points
HN discussionSubmitted Establishing collaboration across LLM Agents when context is close to saturation as a story · 2 points
HN discussionSubmitted What changes when you turn a Linux box into a router as a story · 2 points
HN discussionSubmitted Defeating Context Fatigue with Agentic Scaffolding as a story · 2 points
HN discussionSubmitted Keeping Secrets from Claude Code as a story · 2 points
HN discussionSubmitted Bubblewrap: A nimble way to prevent agents from accessing your .env files as a story · 2 points
HN discussionSubmitted Using network namespaces to discover how Claude Code scrapes as a story · 1 points
HN discussionSubmitted Avoiding wasteful electricity use while self hosting LLMs as a story · 1 points
HN discussionSubmitted Where did my 128GB of video RAM go? AMD GPU BIOS gotcha for LLM builders as a story · 1 points
HN discussionSubmitted Giving AI Agents SSH access without giving them your secret keys as a story · 1 points
HN discussionSubmitted Giving AI agents SSH access without giving up your keys as a story · 1 points
HN discussionSubmitted Building operation agents that SSH into servers to diagnose and fix things as a story · 1 points
HN discussion