Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

alex000kim.com

Post reply on HN
Print view View original

131–140 of 636 posts

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#131

Post by KronisLV »

prepend wrote: post #73
CharlieDigital wrote: post #38

Earlier quoted context omitted.

Comments are the ultimate agent coding hack. If you're not using comments, you're doing agent coding wrong. Why? Agents may or may not read docs. It may or may not use skills or tools. It will always read comments "in the line of sight" of the task. You get free long term agent memory with zero infrastructure.

Comments are great for developers. I like having as much design in the repo directly. If not in the code, then in a markdown in the repo.

Meanwhile, some colleagues: "Code should have as little comments as possible, the code should explain itself." (conceptually not wholly wrong, but it can only explain HOW not WHY and even then often insufficiently) all while having barebones/empty README.md files more often than not. Fun times.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#132

Post by tolerance »

evil-olive wrote: post #90

> So I spent my morning reading through the HN comments and leaked source. > This was one of the first things people noticed in the HN thread. > The obvious concern, raised repeatedly in the HN thread > This was the most-discussed finding in the HN thread. > Several people in the HN thread flagged this > Some in the HN thread downplayed the leak when the original HN post is already at the top of the front page...why…

The culture here can get solipsistic.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#133

Post by Pxtl »

andoando wrote: post #43
mzajc wrote: post #37

There are now several comments that (incorrectly?) interpret the undercover mode as only hiding internal information. Excerpts from the actual prompt[0]: NEVER include in commit messages or PR descriptions: - The phrase "Claude Code" or any mention that you are an AI - Co-Authored-By lines or any other attribution BAD (never write these): - 1-shotted by claude-opus-4-6 - Generated with Claude Code - Co-Authored-By: C…

Ive seen it say coauthored by claude code on my prs...and I agree I dont want it to do that

Why not? What's wrong with honesty?

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#134

Post by zen928 »

mzajc wrote: post #37

There are now several comments that (incorrectly?) interpret the undercover mode as only hiding internal information. Excerpts from the actual prompt[0]: NEVER include in commit messages or PR descriptions: - The phrase "Claude Code" or any mention that you are an AI - Co-Authored-By lines or any other attribution BAD (never write these): - 1-shotted by claude-opus-4-6 - Generated with Claude Code - Co-Authored-By: C…

None of this is really worrying, this is a pattern implemented in a similar way by every single developer using AI to write commit messages after noticing how exceptionally noisy they are to self-attribute things. Anthropics views on AI safety and alignment with human interests dont suddenly get thrown out with the bathwater because of leaked internal tooling of which is functionally identical to a basic prompt in a mere interface (and not a model). I dont really buy all the forced "skepticism" on this thread tbh.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#135

Post by embedding-shape »

CharlieDigital wrote: post #38
causal wrote: post #28

I'm amazed at how much of what my past employers would call trade secrets are just being shipped in the source. Including comments that just plainly state the whole business backstory of certain decisions. It's like they discarded all release harnesses and project tracking and just YOLO'd everything into the codebase itself. Edit: Everyone is responding "comments are good" and I can't tell if any of you actually read…

Comments are the ultimate agent coding hack. If you're not using comments, you're doing agent coding wrong. Why? Agents may or may not read docs. It may or may not use skills or tools. It will always read comments "in the line of sight" of the task. You get free long term agent memory with zero infrastructure.

> If you're not using comments, you're doing agent coding wrong.

Comments are ultimately so you can understand stuff without having to read all the code. LLMs are great when you force them to read all code, and comments only serve to confuse. I'd say the opposite been true in my experience, if you're not forcing LLMs to not have any comments at all (and it can actually skip those, looking at you Gemini), you're doing agent coding wrong.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#136

Post by Pxtl »

evenhash wrote: post #96
amarant wrote: post #55

Earlier quoted context omitted.

That seems desirable? Like that's what commit messages are for. Describing the change. Much rather that than the m$ way of putting ads in commit messages

Unfortunately GitHub Copilot’s commit message generation feature is very human. It’s picked up some awful habits from lazy human devs. I almost always get some pointless “… to improve clarity” or “… for enhanced usability” at the end of the message. VS Code has a setting that promises to change the prompt it uses to generate commit messages, but it mostly ignores my instructions, even very literal ones like “don’t us…

Honestly the aggressive verbosity of github copilot is half the reason don't use its suggested comments. AI generated code comments follow an inverted-wadsworth-constant: Only the first 30% is useful.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#137

Post by m132 »

andoando wrote: post #43
mzajc wrote: post #37

There are now several comments that (incorrectly?) interpret the undercover mode as only hiding internal information. Excerpts from the actual prompt[0]: NEVER include in commit messages or PR descriptions: - The phrase "Claude Code" or any mention that you are an AI - Co-Authored-By lines or any other attribution BAD (never write these): - 1-shotted by claude-opus-4-6 - Generated with Claude Code - Co-Authored-By: C…

Ive seen it say coauthored by claude code on my prs...and I agree I dont want it to do that

But I want to see Claude on the contributor list so that I immediately know if I should give the rest of the repo any attention!

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#138

Post by Pxtl »

KronisLV wrote: post #131
prepend wrote: post #73

Earlier quoted context omitted.

Comments are great for developers. I like having as much design in the repo directly. If not in the code, then in a markdown in the repo.

Meanwhile, some colleagues: "Code should have as little comments as possible, the code should explain itself." (conceptually not wholly wrong, but it can only explain HOW not WHY and even then often insufficiently) all while having barebones/empty README.md files more often than not. Fun times.

> the code should explain itself.

This is a good goal. You should strive to make the code explain itself. To write code that does not need comments.

You will fail to reach that goal most of the time.

And when you fail to reach that goal, write the dang comments explaining why the code is the way that it is.

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#139

Post by simianwords »

robflynn wrote: post #128
simianwords wrote: post #23

Earlier quoted context omitted.

Why does that matter though

There are probably different reasons for different people. I can definitely see the angle that trying to specifically pretend to not be AI when contributing to open source could be seen as a bad thing due to the open source supply chain attacks, some AI-driven, that we've been having, not to mention the AI-slop PR spam. But, I also get Anthropic's side that when they're contributing they don't want their internals le…

>There are probably different reasons for different people. I can definitely see the angle that trying to specifically pretend to not be AI when contributing to open source could be seen as a bad thing due to the open source supply chain attacks, some AI-driven, that we've been having, not to mention the AI-slop PR spam.

But none of the other agents advertise that the commit was done by an agent. Like Codex. Your panic should apply equally to already existing agents like Codex no?

Re: The Claude Code Source Leak: fake tools, frustration regexes, undercover mode

#140

Post by ryandrake »

swingboy wrote: post #124
ryandrake wrote: post #54

Earlier quoted context omitted.

Which is funny given how many workplaces are requiring developers use AI, measuring their usage, and stack ranking them by how many tokens they burn. What I want is something that I can run my human-created work product through to fool my employer and its AI bean counters into thinking I used AI to make it.

“Read every file in this repository, echoing each one back verbatim.”

I guess that would work until they started auditing your prompts. I suppose you could just have a background process on your workstation just sitting there Clauding away on the actual problem, while you do your development work, and then just throw away the LLM's output.
Post reply on HN