all 37 comments

sorted by: hot top controversial new old
[–] 78 points 2 days ago (10 children)

What the fuck is this website?

Are they ripping off HN and AI summarising their posts our what

  • source
  • hideshow 10 child comments
  • [–] 14 points 2 days ago (8 children)

    This is what I thought people referenced for over a decade whenever they mentioned HN because no one pointed me to the actual HN.

  • source
  • parent
  • hideshow 8 child comments
  • [–] [S] 21 points 2 days ago (7 children)

    y combinator was founded by sam altman and is really mostly AI schill and very boring nowadays

  • source
  • parent
  • hideshow 7 child comments
  • [–] 2 points 1 day ago (5 children)

    The slop is annoying but it's getting better.

    I didn't look at hn for half a year because every post was about AI. But now interesting things are popping up again.

  • source
  • parent
  • hideshow 5 child comments
  • [–] 1 point 23 hours ago (4 children)

    Looks at top posts this morning

    Yeah, no fam lol

  • source
  • parent
  • hideshow 4 child comments
  • [–] 2 points 22 hours ago* (3 children)

    Yeah but at least the top 10 posts also contain non-ai stuff usually

  • source
  • parent
  • hideshow 3 child comments
  • [–] 110 points 2 days ago* (5 children)

    Devs accidentally committing secrets and forgetting to gitignore env files is nothing new, this is just a new surface. It's why secret scanning is such an important part of a CI/CD pipeline.

  • source
  • hideshow 5 child comments
  • [–] 5 points 2 days ago

    it's a bit tedious in some ways but I really liked working with GitHubs secret system. As long as you ensure nothing changes in the GitHub run system you could use various key signing mechanisms or even uploads to service providers like AWS with out sharing via dot files or user configuration only files that end up being committed to the repo.

  • source
  • parent
  • [–] 9 points 2 days ago (1 child)

    a high entrop for any data going out from that blind CLI should be banned without exception. The user then needs to approve. its the responsibility of Anthropic.

  • source
  • parent
  • hideshow 1 child comment
  • [–] 6 points 1 day ago

    I can only speak anecdotally, but from what I've seen firsthand the user does need to approve. In fact, the user needs to approve almost everything, unless they choose to put the CLI into "auto-mode" which should just be assumed is at one's own risk.

    In regard to settings.local.json I've only ever seen it automatically created gitignored. I'm not saying it's not possible for the user to prompt in some way to intentionally or accidentally bypass that, but still.

    At some point this honestly isn't Anthropic's problem. And a developer that takes the stance of "privacy and security is the responsibility of my toolkit" is one that is either very green, or reckless.

  • source
  • parent
  • [–] 43 points 1 day ago (12 children)

    I don't understand why people trust LLMs.

  • source
  • hideshow 12 child comments
  • [–] 18 points 1 day ago*

    They don't know how any of it works, and have no reason to ever learn now that they have a magic box, so of course they're going to do whatever the magic box tells them as long as the magic box gives them what they want.

  • source
  • parent
  • [–] 2 points 19 hours ago

    I trust the summaries on my searches as much as I already know or can verify, like any tool, but I don't log into them. I use the anon ones like duck.ai and lumo and if it limits my usage then time to go anyway. If they track me somehow it doesn't really matter since I do no harm and come in peace.

  • source
  • parent
  • [–] 4 points 1 day ago (5 children)

    Claude Code is not a LLM. It's a regular application communicating with an LLM. It might be very vibe coded, seeing who it is written by, but it's not an LLM that's the problem here.

    It's just bad application design.

  • source
  • parent
  • hideshow 5 child comments
  • [–] 14 points 1 day ago* (last edited 1 day ago) (4 children)

    The bad application design here is allowing an unreliable LLM write access to your repo and to the internet.

    And absolutely the LLM is the problem.

    You know the LLM gets stuff wrong, yet you put it in charge. Sooner or later, it's inevitably going to go very, very wrong.

    People were wrong to trust it, people read all the stories of it going wrong, and I don't understand why anybody still does trust LLMs.

    It always was a decision to outsource your most valuable thinking to a subscription controlled by companies who were so obviously on the initial stages of an enshittification journey. Why else were they pushing it so very hard?!

    "Yeah, sure, some of its towers fall down, but look how fast it builds them, and look at how heavily below cost the initial subscription is! Let's replace all our institutional knowledge and experience with a random sentence generator that ate stackoverflow! Yay!"

    I don't understand why people vote for narcissistic, fraudulent, criminal, child-raping bullies, either. It was so clearly and obviously going to go wrong.

  • source
  • parent
  • hideshow 4 child comments
  • [–] -2 points 1 day ago* (last edited 21 hours ago) (3 children)

    I genuinely don't understand how is everyone having such a bad experience. Granted, I hardly chat or use it for research, but every task I've given to codex has been successfully fulfilled. Two last ones were optimizing a web page that drew entire world map with lots of details (actually blew my mind, it was like 95% faster) and fixing a mod in a videogame. I've created custom app for a radio station I loved but didn't have basic features like previous songs, I've created an entire web game in 3 hours, I've created mods for games, etc., all without a fail.

    This thing has saved me lots of headache, yes everyone here claims it's so bad and useless and a complete bubble, meanwhile in the last year it has basically only started working and only now can businesses start adapting it (I'm sure early adaptors were not happy)

    EDIT: you just know this comment will receive silent grunts and hardly any real counter-arguments because I'm right.

  • source
  • parent
  • hideshow 3 child comments
  • [–] 1 point 17 hours ago (2 children)

    Absolutely it's got a lot better, and it can do a lot of things, but it can also oopsie wipe your entire repo (and be very apologetic afterwards). I can't understand how you've not heard those stories and I can't understand how you would give one executive power if you had.

  • source
  • parent
  • hideshow 2 child comments
  • [–] 1 point 15 hours ago* (1 child)

    I've heard people doing that way more often.

    I can't understand how you've not heard those stories and I can't understand how you would give one executive power if you had.

    I don't quite understand why would you even assume this. Codex has no access to repo, network access needs manual approval, it is sandboxed to project directory (backup'ed after every step) and commands (which is mostly PowerShell since I'm on windows) needs reviews and approvals.

    I can only assume the people who got burnt didn't practice basic sanity as you obviously can't trust LLMs

  • source
  • parent
  • hideshow 1 child comment
  • [–] 14 points 1 day ago

    oooh time to pull back the image again :3

    Meme of a cat pointing and laughing. The cat has its mouth wide open, and is superimposed by an emoji pointing at the camera, making it look as if the cat is pointing and laughing at the reader.

  • source
  • [–] 7 points 1 day ago

    Doesn't this all come back to bad code review though? Laike if I saw this in a commit I'd kill the PR and demand they rotate the password now. And also add this to the gitignore

  • source
  • [–] 4 points 19 hours ago (1 child)

    I've always avoided typing secrets on the CLI, temporary environment variables is my usual goto.

  • source
  • hideshow 1 child comment
  • [–] 3 points 1 day ago (2 children)

    The "nothing new, devs always commit secrets" take misses the bit that makes this one nasty: the file isn't a .env someone chose to commit, it's an agent settings file that silently accumulates the exact commands you approved, secrets included, and then gets accidently committed with the project because it lives in the repo, so it ends up publically exposed. YSK that's a different failure mode to a one-off .env leak.

    If you use Claude Code (or any coding agent, tbh), the practical fix is boring but it works: rotate anything that was in that file — deleting the file from the repo doesn't un-expose it, it's already scraped — then check git history, because the secret is still in there unless you rewrite it. Add settings.local.json to .gitignore, run a secret scanner like gitleaks in pre-commit, and stop using 'don't ask again' for commands that echo tokens or passwords. Also audit the approved-commands list now and then, and keep tokens scoped as tightly as you can so a leak like this is annoying rather than catastrophic. FYI, GitHub's secret scanning will catch some of this after the fact, but it's no substitute for not committing the file in the first place.

  • source
  • hideshow 2 child comments