I agree, Claude has been pretty great at explaining code. It even does well at explaining to me old code that I wrote by hand — including both non-intuitive quirks and flaws.
Claude in its default configuration has untapped potential for explaining and documenting code because it defaults to writing no comments. I added this to my global CLAUDE.md and so far so good:
# Comments
Keep existing comments unless they're wrong
or stale. Err slightly toward adding short
explanatory comments for non-obvious code.
The default for Claude today is "no comments". Here's a conversation I had with Claude about it recently:
---
Me: I've notice that Claude is deleting my comments and tends not to insert many of its own. I don't want to go too crazy, but can we modify CLAUDE.md to dial up the comments a little? Like, try not to delete comments that are still relevant, and add a few explanatory comments.
Claude: [... proposal for modifying CLAUDE.md ...]
Claude: Want me to apply this, tweak the wording, or place it differently? Note that your global ~/.claude/CLAUDE.md-style instructions (visible to me as system guidance) currently say "default to writing no comments" — the project-level rule above will override that for this repo, which is what you want.
Me: Where is this rule that says "default to writing no comments"? That seems crazy?
Claude: That text is part of the system prompt I'm given by Claude Code itself — it's not in any file in your project or in your ~/.claude/ config. It's baked into the harness's default instructions to the model.
Claude: Specifically, two lines from my system prompt:
Claude: Under "Doing tasks": "Default to writing no comments. Only add one when the WHY is non-obvious..."
Claude: Under "Text output": "In code: default to writing no comments. Never write multi-paragraph docstrings or multi-line comment blocks — one short line max."
By default, Claude is set to avoid comments. Eventually I got tired of it deleting my own explanatory comments and overrode the behavior with an addition to CLAUDE.md.
I think Claude is just behaving like all those programmers who make a VERY BIG DEAL about how much they HATE HATE HATE comments that might reiterate what the code does so will go to extreme measures to avoid them.
I didn't either. This is an ancient debate that can never be resolved completely, though — because the articles that HN submissions point to don't follow a style guide and there are always assumptions about audience priors. Best to just resolve it and move on.
If you are a candidate who wants to be hired, and your target employers use LLMs to filter resumes, then an LLM-generated resume that the employer LLM-powered resume filters favor is "better" — as in "more likely to get you the job".
At some point, there will be a successful copyright infringement suit against an LLM user who redistributes infringing output generated by an LLM. It could be the NYTimes suit, or it could be another, but it's coming — after which the industry will face a Napster-style reckoning.
What comes next? Perhaps it won't be that hard to assemble a proprietary licensed corpus and get decent performance out of it. Look at all the people already willing to license their voices.
> Because having access to the condensed knowledge of humanity might be more valuable for society then having access to Lars Ulrich's shitty drumming.
Under the current copyright regime, nothing's stopping you from condensing that knowledge yourself and publishing in the public domain. But that would be a lot of work for you, wouldn't it? And I suppose you'd rather do work you'd get paid for.
When society decides AI slop will be the only item on the menu, then copyright will die.
I deliberatly formulated that channeling myself as the kid who actually found his drumming valuable but didn't have the money to buy (all) of it. Who was annoyed at society deciding I should not have it.
So I still don't have the answers but the stakes have certainly gotten bigger.
OpenAI's valuation is more than basically all traditional media companies combined. Nvidia could buy the NYTimes with a month's worth of profits. The top 8 companies in the S&P 500 all benefit more from LLMs being successful than strict copyright enforcement. Congress has very broad power over copyright law. If a suit is successful there is a lot of money and power to be deployed to change copyright law.
Exactly. So just buy it. They have the money or does Sam need a moonbase to complete his villain arc. Any of these AI companies could come out and start paying creators a licensing fee. Instead of being forced to pay damages which is their current approach
If we have to devolve into a tech dystopia, the least they could do is make it interesting. The billionares should get into a lunar robot war, corporate space wars would make a great drama. Maybe if they're busy playing Star Wars they'll forget about the rest of us for a while and we can repurpose all that wealth.
file sharing became far less popular and ubiquitous as a result of their popularity.
they tweaked the model — originally users download a temporary copy from central servers instead of p2p, then later to users rent licensed copies of media instead of pirated copies.
i’m tired of seeing this as an argument on HN — that because something didn’t hit 100% that implies it was a failure and not worth doing or something.
the fact that a limited subset of people still do filesharing is not evidence that the napster case had no effect.
(spotify didn’t exactly start out squeaky clean with how they built out their repertoire iirc).
The Bittorrent ecosystem is still very much around. I’m a cinephile who has a collection of nearly a thousand films in Blu-Ray image format, and 95% of that is off a tracker that is open even, not private.
And Soulseek is still known as the P2P source where you can find all kinds of obscure music.
> The Bittorrent ecosystem is still very much around.
The point is: When Napster was around, everyone was running it all the time from their dorm rooms; it was ubiquitous. Now most people run something like Spotify or Netflix instead; piracy is niche, streaming is ubiquitous.
I’m well aware of that societal change, but the OP asked about an “active filesharing app that’s still in use today”, and if there are Bittorrent communities with so many seeders that one can get almost any film in a matter of minutes, then that fits the definition.
Using Spotify or Netflix as the example of people getting cold to file sharing is odd. People use Spotify and Netflix because piracy is a service problem, and streaming apps made it a lot less friction is get music and video than running LimeWire.
Notably, Spotify did not exist and Netflix did not stream video until long after the Napster suit.
You are comparing the fight between a p2p program and the entire music industry with the fight between the entire LLM industry and a newspaper. Notice how the order seems inconsistent.
reply