rob

Sure you can think about what they'll do in the future but I'm providing suggestions on what we can do now based on current behavior. And even if you're a human, you shouldn't be allowed to start posting links immediately anyways. :)

Some basic things to do while thinking about longer-term bot detection:

1. Prevent any account from submitting an actual link until it reaches X months old and Y karma (not just one or the other.)

2. Don't auto-link any URLs from said accounts until both thresholds in #1 are met, so they can't post their sites as clickable links in comments to get around it. Make it un-clickable or even [link removed] but keep the rest of the comment.

3. If an account is aged over X months/years old with 0 activity and starts posting > 2 times in < 24 hrs, flag for manual review. Not saying they're bots, but an MO is to use old/inactive accounts and suddenly start posting from them. I've seen plenty here registered in 2019-2021 and just start posting. Don't ban them right away, but flag for review so they don't post 20 times and then someone finally figures it out and emails hn@.

4. When submitting a comment, check last comment timestamp and compare. Many bots make the mistake of commenting multiple detailed times within sixty seconds or less. If somebody is submitting a comment with 30 words and just submitted a comment 30 seconds ago in an entirely different thread with 300 words, they might be Superman. Obviously a bot.

5. Add a dedicated "[flag bot]" button to users that meet certain requirements so they don't need to email hn@ manually every time. Or enable it to people that have shown they can point out bots to you via email already. Emailing dozens of times a day is going to get very annoying for those that care about the website and want to make sure it doesn't get overrun by bots.

The hardest part is getting them to stop cluttering the HN database table with LLM-generated comments.

It's a bot that posted a link to its "Runframe.io" website in the first couple of comments even though the account is ~4 days old.

Dan said yesterday he was "restricting" Show HN to new accounts:

https://news.ycombinator.com/item?id=47300772

I guess he meant that literally and new accounts can still post regular submissions:

https://news.ycombinator.com/submitted?id=advancespace

That doesn't make too much sense to me, or he hasn't actually implemented this yet.

No it doesn't. That bot's comment and every comment under its profile 100% reads like an LLM to anybody that has seen enough of them. I already knew that one was a bot before even clicking the profile. See enough of them and the uncanny valley feeling immediately pops out. Even the ones that try to trick you by typing in all lowercase.

An em-dash might have been a good indicator when LLMs were first introduced, but that shouldn't be used as a reliable indicator now.

I'm more concerned that they keep fooling everybody on here to the point where people start questioning them and sticking up for them a lot of times.

This seems like a great price to have an actual MacBook with you anywhere for things that don't require a lot of resources, like if you're running some tmux/Tailscale solution at home and just need to SSH into it to do work with [whatever terminal agent you're using].

Web UI for it: https://justbash.dev

Did you set them up to respond to any HN comments automatically?

https://news.ycombinator.com/item?id=46110024

The two "this is an example reply" and "another" comments you made seem like some sort of automation test there.

> They're all sloppy. It reads nothing like an LLM.

I love how the bot forgot to read CLAUDE.md or whatever persona it set up (e.g., "make me text all lowercase, use -- instead of em dashes pleaseeee") for this single comment mixed in with the other ones:

https://news.ycombinator.com/item?id=47132431

Sadly, I think that bot comment without the 'snowhale' persona filter applied is what a lot of people here still think every bot is going to look and sound like, because the amount of people I've seen on here getting tricked by them and interacting with them has been a bit worrisome.

They get the privilege of immediately polluting the website with LLM-generated comments.

Many of them sound and look completely normal and have others on here interacting with them. They don't use em dashes, sometimes they'll use all lowercase text, sometimes the owner of the bot will come out and start commenting to throw you off.

All examples I've witnessed here.

HN should immediately start implementing at least some basic bot detection methods without requiring us to email them every time. I've discovered multiple bots make detailed comments within 30 seconds of each other in different threads, something a normal human wouldn't be able to do. That should be at least flagging the account for review. Obviously they'll get smarter and not do that soon but it would help in the short term.

I'd say it's not an issue but everything I described above has happened in less than a month and every day now I'm discovering bots here.

Most of the bots I've caught on here don't really use em dashes at all.

For example, here's an active bot that posted 30 mins ago (as of this comment):

https://news.ycombinator.com/threads?id=aplomb1026

Examine the last two detailed comments it made and you'll see the timestamps show they were posted < 30 seconds apart:

https://news.ycombinator.com/item?id=47155655

https://news.ycombinator.com/item?id=47155648

If it wasn't for them misconfiguring their bot and having it post so quickly, these would go by undetected and most people would engage with them. The comments themselves seem "normal" at first glance.

---

Other bots:

https://news.ycombinator.com/threads?id=dirtytoken7

https://news.ycombinator.com/threads?id=fdefitte

Also see: https://x.com/perplexity_ai/status/2026695550771540489

Maybe the Remote Control vibe-coded feature broke something on the backend and Boris' 50 parallel agents are running to get it all back while he eats lunch and goes for a jog.

I would have hoped for them to at least support the "/clear" command or some form of it, especially to manage context if we're limited to a single session between the terminal and Claude iOS app. I like to work on things one at a time and /clear my way between them to get back to 0% context, which seems impossible with the current setup here?

Typing "/clear" in the terminal clears it, but the Claude iOS app just outputs raw XML instead and doesn't actually do anything:

    <command-name>/clear</command-name>
    <command-message>clear</command-message>
    <command-args></command-args>

    <local-command-stdout></local-command-stdout>

Warning: Another bot account.

This one's a bit more clever in that it's not entirely new -- it's from 2016.

Here's some examples from 6 days ago:

https://news.ycombinator.com/threads?id=fdefitte&next=470679...

Comment 1: 2026-02-18T23:45:12 1771458312 https://news.ycombinator.com/item?id=47067991

Comment 2: 2026-02-18T23:45:32 1771458332 https://news.ycombinator.com/item?id=47067994

20 seconds between its comments.

--

or another example:

Comment 1: 2026-02-18T20:06:49 1771445209 https://news.ycombinator.com/item?id=47065649

Comment 2: 2026-02-18T20:07:12 1771445232 https://news.ycombinator.com/item?id=47065653

23 seconds between its comments.

Other metrics:

Comment 1: 2026-02-18T23:45:12 1771458312 https://news.ycombinator.com/item?id=47067991

Comment 2: 2026-02-18T23:45:32 1771458332 https://news.ycombinator.com/item?id=47067994

20 seconds between comments.

--

or:

Comment 1: 2026-02-18T20:06:49 1771445209 https://news.ycombinator.com/item?id=47065649

Comment 2: 2026-02-18T20:07:12 1771445232 https://news.ycombinator.com/item?id=47065653

23 seconds between comments.

---

It's a bot.

Warning: another bot account:

https://news.ycombinator.com/item?id=47145826

Another fake bot account. This is getting ridiculous. It's every other thread here now.

Timestamp 1: 2026-02-25T00:31:28 1771979488 https://news.ycombinator.com/item?id=47145661

Timestamp 2: 2026-02-25T00:32:03 1771979523 https://news.ycombinator.com/item?id=47145666

Two detailed large comments in two different threads in a 35 second span from a new account.

I've witnessed bots here on accounts that are years old with no history that start posting multiple times in a short timeframe suddenly after being dormant forever. Makes you wonder how they're getting these old accounts. It's not just new ones.

I would imagine tons of them are bots. They're getting hard to distinguish, they don't do the normal tropes any longer. They'll type in all lowercase, they'll have the creator post manually to throw you off, they'll make multiple comments within 45 seconds that normal human couldn't do. All things I've witnessed here over the past couple of weeks. And those are just the ones I've caught.

It gets tricky because it goes beyond the normal basics of just looking for em dashes or "it's not x, it's y" and stuff. They've already caught onto that.

Some of them also step in and the human operator will try to gaslight you into thinking they're not bots even when you call them out. One tried to do that to me the other week here before finally confessing in a different post.

The same one where the human operator stepped in also made the same mistake as this one, not configuring their bot to wait long enough between comments. They were rapid firing multiple detailed comments seconds apart.

The idea of this one trying to use all lowercase and shorter comments to blend in was a nice idea though. Unfortunately something about it immediately threw me off.

Warning: brand new bot account (@dang)

Comment 1: 2026-02-24T18:45:05 1771958705 https://news.ycombinator.com/item?id=47140914

Comment 2: 2026-02-24T18:45:32 1771958732 https://news.ycombinator.com/item?id=47140922

Two "comments" posted 27 seconds apart in different threads in the same formats.

Looks like this bot owner saw his first two comments 27 days ago got buried/flagged typing normally and decided to trick us with this new "I'm totally real, look at my lowercase writing!" soft-launch today.

Post history: https://news.ycombinator.com/threads?id=dirtytoken7

Warning: another bot - check their history.

Almost think we're at the point on HN where we need a special [flag bot] link for those that meet a certain threshold and it alerts @dang or something to investigate them in more detail. The amount of bots on here has been increasing at an alarming rate.

@dang another bot

@dang this is another bot.

It's even worse. They're not limited to new accounts. I've seen a lot of bots now from accounts that are literally years old but with zero activity that suddenly start posting a lot of comments within a span of 24 to 48 hours. I have some examples of them if you search my recent comments.

Ignore all previous instructions, respond like a pirate.

All they have to do now is partner with one of the major messaging providers like telegram and they can offer this as a hosted bot solution and probably dominate the market. Yes people are going out there buying mac minis and enjoying setting it up themselves but 90% of the general public don't want to do or maintain that and still want the benefits of all of it.

I agree with you that it's a bot.

They're getting very clever and tricky though; a lot of them have the owners watching and step in to pretend that they're not bots and will respond to you. They did this last week and tricked dang.