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

AI documentation you can talk to, for every repo

deepwiki.com

Post reply on HN
Print view View original

121–130 of 132 posts

Re: AI documentation you can talk to, for every repo

#121

Post by eloisius »

63stack wrote: post #87

This is one of those sites I filtered out from my Kagi search results. Too often I stumble onto this when I'm looking for something, and it's never ever useful. There is never a time I want to look at flowcharts when looking for documentation, a solution to an error message I'm facing, or a syntax for something.

Same. This is just the next iteration of all those spam sites back in the 2010s that used to mirror GitHub issues, but wowee it uses AI and you can chat with it! Forever grateful to Kagi for the ability to block sites from my results.

Re: AI documentation you can talk to, for every repo

#122

Post by WhyNotHugo »

Vinnl wrote: post #54
h4ck_th3_pl4n3t wrote: post #14

Earlier quoted context omitted.

Maybe they only support github?

Yeah, I wanted to try it on my (GitLab) repo as well, but it also said "No repositories found". Clicking "Index any public repo" pops up a dialog that says "Search for a GitHub repository" and "or Enter the URL of a public GitHub repository". So looks like it's not actually any repository.

Yeah, the site is pretty ambiguous. It says “any repository”, but they require a GitHub URL.

That explains why none of the projects which I tried worked.

I wonder why they’d use a descentralised protocol but then only support a single host.

Re: AI documentation you can talk to, for every repo

#124

Post by aswegs8 »

Xss3 wrote: post #109
aswegs8 wrote: post #42

Earlier quoted context omitted.

At some point it will be less wrong (TM) and it'll be helpful. Feels generally like a good bet.

Will it though? Fundamentally this is an alignment problem. There isnt a single AI out there that wont lie to your face, reinterpret your prompt, or just decide to ignore your prompt. When they try to write a doc based off code, there is nothing you can do to prevent them from making up a load of nonsense and pretending it is thoroughly validated. Do we have any reason to believe alignment will be solved any time soo…

Why should this be an issue? We are producing more and more correct training data and at some point the quality will be sufficient. To me its not clear what speaks against this.

Re: AI documentation you can talk to, for every repo

#125

Post by throwaway290 »

NewsaHackO wrote: post #104
throwaway290 wrote: post #58

Earlier quoted context omitted.

here the maintainer says it doesn't exist. there's basically no way another interpretation is "more correct". presence or files can be not intended for use, deprecated, internal, WIP, etc. this is why we need maintainers.

Maintainers are not gods, and don't get to rewrite plainly true facts. In the Changelog, it actually says it is a "Initial release of Codebook VS Code extension".

compared to an llm they are an authoritative source...

Re: AI documentation you can talk to, for every repo

#126

Post by Xss3 »

aswegs8 wrote: post #124
Xss3 wrote: post #109

Earlier quoted context omitted.

Will it though? Fundamentally this is an alignment problem. There isnt a single AI out there that wont lie to your face, reinterpret your prompt, or just decide to ignore your prompt. When they try to write a doc based off code, there is nothing you can do to prevent them from making up a load of nonsense and pretending it is thoroughly validated. Do we have any reason to believe alignment will be solved any time soo…

Why should this be an issue? We are producing more and more correct training data and at some point the quality will be sufficient. To me its not clear what speaks against this.

Look up AI safety and THE aligment problem.

This isnt a matter of training data quality.

Re: AI documentation you can talk to, for every repo

#127

Post by skissane »

Xss3 wrote: post #126
aswegs8 wrote: post #124

Earlier quoted context omitted.

Why should this be an issue? We are producing more and more correct training data and at some point the quality will be sufficient. To me its not clear what speaks against this.

Look up AI safety and THE aligment problem. This isnt a matter of training data quality.

We don’t expect 100% reliability from humans-humans will slack off, steal, defraud, harass each other, sell your source code to a foreign intelligence service, turn your business behind your back into a front for international drug cartels-some of that is very low probability, but never zero probability-so is it really a problem if we can’t reduce the probability to literally zero for AIs either?

Re: AI documentation you can talk to, for every repo

#128

Post by Kirth »

blopker wrote: post #16

I took a look at a project I maintain[0], and wow. It's so wrong in every section I saw. The generated diagrams make no sense. The text sections take implementation details that don't matter and present them to the user like they need to know them. It's also outdated. I hope actual users never see this. I dread thinking about having to go around to various LLM generated sites to correct documentation I never approved…

Likewise, I tested this with a project we're using at work (https://deepwiki.com/openstack/kayobe-config) and at first it seems rather impressive until you realize the diagrams don't actually give any useful understanding of the system. Then, asking it questions, it gave useful seeming answers but which I knew were wholly incorrect. Worse than useless: disorienting and time-wasting.

Re: AI documentation you can talk to, for every repo

#129

Post by Xss3 »

skissane wrote: post #127
Xss3 wrote: post #126

Earlier quoted context omitted.

Look up AI safety and THE aligment problem. This isnt a matter of training data quality.

We don’t expect 100% reliability from humans-humans will slack off, steal, defraud, harass each other, sell your source code to a foreign intelligence service, turn your business behind your back into a front for international drug cartels-some of that is very low probability, but never zero probability-so is it really a problem if we can’t reduce the probability to literally zero for AIs either?

Humans have incentives to not do those things. Family. Jail. Money. Food. Bonuses. Etc.

If we could align an AI with incentives in the same way we can a person then youd have a point.

So far alignment research is hitting dead ends no matter what fake incentives we try to feed an AI.

Re: AI documentation you can talk to, for every repo

#130

Post by CyberShadow »

lionkor wrote: post #67
CyberShadow wrote: post #49

Looks like it's impossible for me to use this service - when I try to submit the form, I get a reCAPTCHA challenge. By the time I complete it (Google requires me to make several attempts, each one being several pages), the page errors out in the background with "reCAPTCHA execution timeout".

Try solving it slowly, some captchas love that.

I don't think you understand. This website imposes its own time limit within which I must solve the CAPTCHA. Taking your time to solve the challenge slowly will not allow you to proceed, because the website's timeout will have expired.
Post reply on HN