I had this happen yesterday to me, and Claude itself was able to recover it via the other conversations... I just had to tell it that it did the work and to find it in its other conversations.
I considered doing that, but my 80+ files were scattered in over 20 large conversations, It would've been too annoying to keep track of which file was extracted, and probably would have exhausted the context window of a chat in no-time.
soon were gonna be the ones adding random typos and grammer errors just to blend in. i skip apostrophes and mispell words on purpose already. its strange how fast sloppy writing starts feeling natural
I don't know if worse grammar could make a difference aside from removing false negatives (ie. nowadays people with good grammar are questioned if they are LLM's or not) but this itself doesn't mean that worse grammar itself means its written by a human. (This paragraph is written by me, a human, Hi :D)
Honestly, first paragraph sounds more human and sincere for sure.
Also adding better "context" into the discussion, than the usual claims/punchlines of marketing-speak.
Maybe it's not exactly the grammar itself but also overall structuring of the idea/thought into the process. The regular output sounds much more like marketing-piece or news-coverage than an individual anyway. I think, people wanna discuss things with people, not with a news-editor.
> I think, people wanna discuss things with people, not with a news-editor.
If I understand you correctly, then Yes I completely agree, but my worry is that this can also be "emulated" as shown by my comment by Models already available to us. My question is, technically there's nothing to stop new accounts from using say Kimi and to have a system prompt meant to not sound AI and I feel like it can be effective.
If that's the case, doesn't that raise the question of what we can detect as AI or not (which was my point), the grand parent comment suggests that they use intentionally bad human writing sometimes to not be detected as AI but what I am saying is that AI can do that thing too, so is intentionally bad writing itself a good indicator of being human?
And a bigger question is if bad writing isn't an indicator, then what is?
Or if there can even be an good indicator (if say the bot is cautious)? If there isn't, can we be sure if the comments we read are AI or not
Essentially the dead-internet-theory. I feel like most websites have bots but we know that they are bots and they still don't care but we are also in this misguided trust that if we see some comments which don't feel like obvious bots, then they must be humans.
My question is, what if that can be wrong? It feels to me definitely possible with current Tech/Models like say Kimi for example, Doesn't this lead to some big trust issues within the fabric of internet itself?
Personally, I don't feel like the whole website's AI but there are chances of some sneaky action happening at distance type of new accounts for sure which can be LLM's and we can be none the wiser.
All the same time that real accounts are gonna get questioned if they are LLM or not if they are new (my account is almost 2 years old fwiw and I got questioned by people esentially if this account is AI or not)
But what this does do however, is make people definitely lose a bit of trust between each other and definitely a little cautious towards each message that they read.
(This comment's a little too conspiratorial for my liking but I can't help but shake this feeling sometimes)
It just is all so weird for me sometimes, Idk but I guess that there's still an intuition between whose human and not and actually the HN link/article iteslf shows that most people who deploy AI on HN in newer accounts use standard models without much care which is the reason why em-dashes get detected and maybe are good detector for sometime/some-people and this could make the original OP's comment of intentionally having bad grammar to sound more human make sense too because em-dashes do have more probability of sounding AI than not :/
It's just this very weird situation and I am not sure how to explain where depending on from whatever situation you look at, you can be right.
You can try to hurt your grammar to sound more human and that would still be right
and you can try to be the way you are because you think that models can already have intentionally bad grammar too/capable of it and to have bad grammar isn't a benchmark itself for AI/not so you are gonna keep using good grammar and you are gonna be right too.
It's sort of like a paradox and I don't have any answers :/ Perhaps my suggestion right now feels to me to not overthink about it.
Because if both situations are right, then do whatever imo. Just be human yourself and then you can back down this statement with well truth that you are human even if you get called AI.
So I guess, TLDR: Speak good grammar or not intentionally, just write human and that's enough or that should be enough I guess.
Hey Chase! Congrats on everything you, Grace, Thomas and the rest of the team built. I know it wasn't always what you expected it to be from the inside, but from the outside nobody saw that. They just saw something amazing. Your Startup School talk is my favorite ever, and I'm lucky I got to work with you all those years ago. You built something incredible, and helped a lot of people.
It wasn't until I read your comment that I was able to pinpoint why the mental exhaustion feels familiar. It's the same kind (though not degree) of exhaustion as formal methods / proofs.
Except without the reward of an intellectual high afterwards.
I feel this too. I suspect its a byproduct of all the context switching I find myself doing when I'm using an LLM to help write software. Within a 10 minute window, I'll read code, debug a problem, prompt, discuss the design, test something, do some design work myself and so on.
When I'm just programming, I spend a lot more time working through a single idea, or a single function. Its much less tiring.
In my experience it's because you switch from writing code to reviewing code someone else wrote. Which is massively more difficult than writing code yourself.
Interesting, I feel the opposite. I always tend to associate askers and extroverts, and feel us introverts are tired all the time because of all the guessing going on during human interactions.
But of course, your opposite takeaway also makes sense!
I found this 10+ years ago, and it was one of the most important things I ever read. As a consummate Guesser, it reframed my perspective completely. I started to be much happier and understanding with Askers.
I also realized how frustrating, as a Guesser, I could be to Askers, and shifted more toward being clear about what I want or need.
My family is almost 100% Asker. When I got to college, I drove Guessers nuts. They thought I was so selfish and would blow up at me (from my perspective) out of nowhere.
"No" is always a perfectly fine and polite answer from my perspective
Guessers don't believe Askers are asking in bad faith at all. If Guessers did believe that, it would be way easier for them to say no to Askers. It's precisely because the Guesser believes in the sincerity of the request that it becomes painful to deny it.
Indeed. It's the immediate assumption that since you're asking me, it must be important to you - otherwise you wouldn't be asking in the first place.
I want to be the kind of person that helps others where it matters, and here you are, asking, thus proving it matters. Refusing becomes really uncomfortable, so I'd rather go out of my way to make it possible for me to agree, or failing that, to help your underlying need as much as I can.
I realize now this is a form of typical mind fallacy - I wouldn't ask you for something if it wasn't really fucking important or I had any other option available, therefore I naturally assume that your act of asking already proves the request is very important to you.
That's the really painful part. They ask you for something, you say 'yes' thinking it's important for the person, only to learn that it wasn't that important at all. It's like giving something that you don't want to give to someone that doesn't need it. Really annoying.
So how would you recommend communicating desires that are less strong than "important"?
I try to include the priority level of my requests inside the question itself, personally. As in, "Hey do you think you could xyz if it's not too much trouble? Not a high priority for me, but it would be convenient is all." Do you recommend something like that?
Having said that, I have become a lot better at being direct these past few years, so I'd likely just say "I'm not able to, sorry. I can recommend some good hotels though".
Default No is fine, just go with it. That’s a huge ask. It was a 2 week stay, that’s a hell no unless you’re my nuclear family then maybe we can discuss it. Even then, there’s some family I don’t want as overnight guests and I usually put up in a nearby hotel when they visit.
No reason to feel guilty saying no when the ask is that large. I feel bad sometimes saying no to small things. Because it’s trivial on the surface and I don’t have a good reason for saying no except I just don’t want to do it. In any case, I like treating no as my default answer to everything then I have to be convinced to say yes (even if it’s a quick internal negotiation with myself).
If you’re consistent, the most abusive askers learn not to ask. The ones that ask with expectations of a yes, the ones that try to make you feel bad for saying no, those people go away. And that’s my ideal position, I’m only being asked for reasonable things so actually end up saying yes more often than I say no.
The askers who make you feel bad don't go away. They go up your org chart or get replaced by similar if your company culture tolerates it. You're the one who goes away or settles.
You are responsible for your feelings and setting your boundaries.
Learning how to set boundaries is something most people learn as they mature. Yeah, not easy. I have especially noticed recently that some of my friends who are mums have learnt how to claim their own needs only after their kids have left home. Some people give too much.
Do you expect others to adivinate what your personal boundaries are?
Do you get frustrated when friends or family make the wrong assumptions?
If you have arseholes in your life that actually make you feel bad, then it is even more important to learn how set boundaries with them. If they don't respect the boundaries you set, or create conflict, then that is often very difficult to resolve.
I struggle with conflict avoiders because they have needs however they often act passive. Yet their hidden expectations remain, and their response if you fail to meet their expectations is often poor. One friend in particular also often guesses wrong to my detriment, instead of asking a simple question.
Do mind readers want others to read minds?
I strongly dislike passive people that blame others for their poor communications.
> I strongly dislike passive people that blame others for their poor communications.
Same. I struggle with the construct specifically because I think I am both an asker and a guesser. I do agree it exists however I can’t bucket myself into either side. The approach I choose to utilize at any given time is a contextual calculation. Do I have a strong opinion? Do I have a sufficient status to assert myself? Do I not care and just want to appease the other person? Do I intentionally want to stroke their ego?
But, choose an approach and use it as a tool. Miscalculations occur leading to outcomes I may not predict or prefer sometimes but that’s just a learning experience for me. I might adjust my internal algorithm for making that calculation in the future. I might decide I just don’t like interacting with that person, and that’s fine too. But I don’t blame anyone or expect them to change for me.
Did you mean to reply to someone else? I don't know where this is coming from as I didn't make these claims.
That said, your comment is disturbing.
It's a obnoxious to "strongly dislike" (read: hate) people who don't have resilient self-esteem. It lacks compassion. And if someone's bullying you, getting platitudes about "responsible for your feelings" and "boundaries" is useless.
Strongly dislike can also mean you just prefer to avoid those people or limit your interactions. It doesn’t mean hate.
If you want people like this to stop avoiding you, it’s an internal adjustment that needs to be made. That’s the responsibility for yourself part. Ignoring you is not hurting the other person one bit, actually they are benefiting from it as they skip dealing with your personality they dislike. It’s not to say they are biased against you, if you were more compatible they may change their stance without thinking about it. That wouldn’t happen if they hated you.
Hate is a strong dislike but that doesn’t mean a strong dislike is hate.
It could mean anything more. Especially given the medium we’re using to communicate, where they chose those words instead of just saying hate. This medium is concise and those words were chosen over the word hate. I think it’s most likely they were chosen to reference to the huge grey area of stuff they could have meant but they didn’t want to explain due to their desire for to keep concise text communications which is what we’re all engaging with online. If we had to explain why we chose every word we chose this mode of communication would be useless.
It's not mind reading. It's basic empathy and respect. Expecting others to understand the norms of social behavior is not smart, but it is perfectly normal. Realizing that many people lack the ability to empathize or socialize politely and dealing with that is an unfortunate consequence of modern society making travel so easy. We're all mixed up and people from totally different cultures need to learn to deal with each other.
If someone goes on to say, "well you ruined my vacation" or something like that, they weren't asking at all, they were demanding and now they're bullying you about having boundaries to try to tear your boundaries down.
People who go out of their way to try to trample your explicitly stated boundaries are abusing you.
So say no, and if they don't take it well, create distance or tell them off. Avoiding conflict in this case is fully to your own detriment.
If, on the other hand, they do take it well, then guess what? They're an asker and are just fully exploring their options and it's no big deal to them that you said no.
Thank you for reposting this, OP. I have been (w)racking my brain trying to find this article and used HN search dozens of times. I couldn't remember what the title was, or the specific terms "ask" and "guess", so it was impossible to find.
This is one of the chief cultural differences between Southern and Northern culture.
Southerners (not transplants) will "ask" without imposition: they "ask" when giving, and "guess" when receiving.
Any inversion of these norms is an affront to "Southern hospitality" and will be met with the equivalent "Bless Your Heart".
Ask what you can do for someone, never what you can have. Assume someone will do right by you (you should never have to ask), and if they don't - people say not so nice things about those folks.
I need to articulate this better when it's not 4 AM, but it's an almost perfect descriptor of the cultural differences.
I guess I don't see the problem? Nothing lasts forever, and everyone involved knew the risks.
That money wasn't purely wasted, it went into salaries and other products. At least half ended in exits and became a part of another company.
The ability to fail and fail big is what makes the SF tech scene special... people aren't afraid to try something audacious. And sure, the world could take-or-leave most of these products, but I don't really see the point in this negative framing.
I disagree. A good framework makes code more maintainable, and makes it so you can focus on what’s important or unique to your product. It certainly makes you faster.
That depends on what you are comparing against. If a given developer is incapable of writing an application without a framework then they will certainly be more productive with a framework.
It’s like a bulldozer is certainly faster than a wheelchair, but somebody else might find them both slow.
Eh. I’ve written plenty of applications by hand before there were good frameworks— win32 apps, old school web applications, “modern” SPA-like apps before there was a React. I’m more productive with React + Tailwind than I was with anything (other than maybe VB6). Being able to reason about your UI as a (mostly) pure function of state is powerful. It reminds me of the simplicity of game development— with a proper rendering layer, your developers can focus mostly on modeling their problem rather than UI complexities.
I run a documentation product, ReadMe. There's a lot of reasons to roll your own, but I'd recommend you also look into a third-party tool like us. One of the biggest reasons to use a product is that the building v1 is easy, but keeping it up to date over time is a lot tougher... you're stuck remembering how to deploy, figuring out a workflow, dealing with multiple versions, etc.
You also just don't get a ton of really great features for your developers... fast typeahead search, AI tools (which your developers increasingly really want), navigation, accessibility and more. ReadMe also lets your developers play around with you API locally and get copy-and-paste code snippets.
(If you're deciding between your own and ReadMe, email me! greg@readme.io; would love to talk)
There's also a free version, and a $79/mo tier. We're also free for open source projects on our higher tiers.
If it's not for you, that's okay! But an increasing number of documentation teams are cross-functional (marketing, sales, engineering, product), and not everyone is comfortable editing content directly in Git and dealing with a release.
Docs are the heart and soul of most devtools, so I think it makes sense a lot of companies want a good product.
I love Tailwind, and I am really sorry Adam and co are going through this. They've built a great product, and it's brought joy back building again for me.
It's really hard to run a company, especially when your product is mostly OSS... Tailwind has helped thousands of companies save (or make) millions of dollars, and AI almost by default uses it to generate beautiful websites. This is such a hard position to be in... to watch your product take off, but your financials plummet. It really sucks how affected the team is after all the good work they've done.
reply