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

Show HN: I built an AI that turns GitHub codebases into easy tutorials

github.com

Post reply on HN
Print view View original

151–160 of 181 posts

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#151

Post by kaycebasques »

cushychicken wrote: post #73
bilalq wrote: post #34

This is actually really cool. I just tried it out using an AI studio API key and was pretty impressed. One issue I noticed was that the output was a little too much "for dummies". Spending paragraphs to explain what an API is through restaurant analogies is a little unnecessary. And then followed up with more paragraphs on what GraphQL is. Every chapter seems to suffer from this. The generated documentation seems mor…

Answers like this are sort of what makes me wonder what most engineers are smoking when they think AI isn’t valuable. I don’t think the outright dismissal of AI is smart. (And, OP, I don’t mean to imply that you are doing that. I mean this generally.) I also suspect people who level these criticisms have never really used a frontier LLM. Feeding in a whole codebase that I’m familiar with, and hearing the LLM give goo…

> hearing the LLM give good answers about its purpose and implementation from a completely cold read

Cold read ability for this particular tool is still an open question. As others have mentioned, a lot of the example tutorials are for very popular codebases that are probably well-represented in the language model's training data. I'm personally going to test it on my private, undocumented repos.

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#152

Post by kaycebasques »

microtonal wrote: post #145
grugagag wrote: post #134

Earlier quoted context omitted.

LLMs excel at some things and work very poorly at others. People working on different problems have had different experiences, sometimes opposite ends of the spectrum.

I think the people who claim 10x-100x productivity improvements are working on tasks where LLMs work really well. There is a lot of development work out there that is relatively simple CRUD and LLMs are very good at it. On the complete opposite end we have designing new algorithms/data structures or extending them in a novel way. Or implementing drivers for new hardware from incomplete specs. LLMs do not do well on t…

Your OpenSCAD experience is an important point in the productivity debates that is often not discussed. A lot of projects that were previously impossible are now feasible. 10 years ago, you might have searched the OpenSCAD docs, watched videos, felt like it was impossible to find the info you needed, and given up. Claude and similar tools have gotten me past that initial blocker many times. Finding a way to unblock 0 to 1 productivity is perhaps as important (or maybe even more important than) as enabling 1 to 10 or 1 to 100.

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#153

Post by kaycebasques »

remoquete wrote: post #141

This is nice and fun for getting some fast indications on an unknown codebase, but, as others said here and elsewhere, it doesn't replace human-made documentation. https://passo.uno/whats-wrong-ai-generated-docs/

My bet is that the combination of humans and language models is stronger than humans alone or models alone. In other words there's a virtuous cycle developing where the codebases that embrace machine documentation tools end up getting higher quality docs in the long run. For example, last week I tried out a codebase summary tool. It had some inaccuracies and I knew exactly where it was pulling the incorrect data from. I fixed that data, re-ran the summarization tool, and was satisfied to see a more accurate summary. But yes, it's probably key to keep human technical writers (like myself!) in the loop.

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#154

Post by iteria »

microtonal wrote: post #145
grugagag wrote: post #134

Earlier quoted context omitted.

LLMs excel at some things and work very poorly at others. People working on different problems have had different experiences, sometimes opposite ends of the spectrum.

I think the people who claim 10x-100x productivity improvements are working on tasks where LLMs work really well. There is a lot of development work out there that is relatively simple CRUD and LLMs are very good at it. On the complete opposite end we have designing new algorithms/data structures or extending them in a novel way. Or implementing drivers for new hardware from incomplete specs. LLMs do not do well on t…

You don't even need such fancy examples. There are plenty of codebases where people are working with code that is over a decade old and has several paradigms all intermixed with a lot of tribal knowledge that isn't documented in code or wiki. That is where AI sucks. It will not be able to make meaningfully change in that environment.

There is also the frontend and tnpse code bases don't need to be very old at all before AI falls down. NPM packages and clashing styles in a codebase and AI has been not very helpful to me at all.

Generally speaking, which AI is a fine enhancement to autocomplete, I haven't seen it be able to do anything more serious in a mature codebase. The moment business rules and tech debt sneak in in any capacity, AI becomes so unreliable that it's faster to just write it yourself. If I can't trust the AI to automatically generate a list of exports in an index.ts file. What can I trust it for?

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#155

Post by remoquete »

kaycebasques wrote: post #153
remoquete wrote: post #141

This is nice and fun for getting some fast indications on an unknown codebase, but, as others said here and elsewhere, it doesn't replace human-made documentation. https://passo.uno/whats-wrong-ai-generated-docs/

My bet is that the combination of humans and language models is stronger than humans alone or models alone. In other words there's a virtuous cycle developing where the codebases that embrace machine documentation tools end up getting higher quality docs in the long run. For example, last week I tried out a codebase summary tool. It had some inaccuracies and I knew exactly where it was pulling the incorrect data from…

Indeed. Augmentation is the way forward.

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#156

Post by simonw »

iteria wrote: post #154
microtonal wrote: post #145

Earlier quoted context omitted.

I think the people who claim 10x-100x productivity improvements are working on tasks where LLMs work really well. There is a lot of development work out there that is relatively simple CRUD and LLMs are very good at it. On the complete opposite end we have designing new algorithms/data structures or extending them in a novel way. Or implementing drivers for new hardware from incomplete specs. LLMs do not do well on t…

You don't even need such fancy examples. There are plenty of codebases where people are working with code that is over a decade old and has several paradigms all intermixed with a lot of tribal knowledge that isn't documented in code or wiki. That is where AI sucks. It will not be able to make meaningfully change in that environment. There is also the frontend and tnpse code bases don't need to be very old at all bef…

When is the last time you tried using LLMs against a large, old, crufty undocumented codebase?

Things have changed a lot in the past six weeks.

Gemini 2.5 Pro accepts a million tokens and can "reason" with them, which means you can feed it hundreds of thousands of lines of code and it has a surprisingly good chance of figuring things out.

OpenAI released their first million token models with the GPT 4.1 series.

OpenAI o3 and o4-mini are both very strong reasoning code models with 200,000 token input limits.

These models are all new within the last six weeks. They're very, very good at working with large amounts of crufty undocumented code.

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#158

Post by voidUpdate »

cushychicken wrote: post #73
bilalq wrote: post #34

This is actually really cool. I just tried it out using an AI studio API key and was pretty impressed. One issue I noticed was that the output was a little too much "for dummies". Spending paragraphs to explain what an API is through restaurant analogies is a little unnecessary. And then followed up with more paragraphs on what GraphQL is. Every chapter seems to suffer from this. The generated documentation seems mor…

Answers like this are sort of what makes me wonder what most engineers are smoking when they think AI isn’t valuable. I don’t think the outright dismissal of AI is smart. (And, OP, I don’t mean to imply that you are doing that. I mean this generally.) I also suspect people who level these criticisms have never really used a frontier LLM. Feeding in a whole codebase that I’m familiar with, and hearing the LLM give goo…

Well companies lock "frontier LLMs" behind paywalls, and I don't want to pay for something that still might not be of any use to me

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#159

Post by GaggiX »

voidUpdate wrote: post #158
cushychicken wrote: post #73

Earlier quoted context omitted.

Answers like this are sort of what makes me wonder what most engineers are smoking when they think AI isn’t valuable. I don’t think the outright dismissal of AI is smart. (And, OP, I don’t mean to imply that you are doing that. I mean this generally.) I also suspect people who level these criticisms have never really used a frontier LLM. Feeding in a whole codebase that I’m familiar with, and hearing the LLM give goo…

Well companies lock "frontier LLMs" behind paywalls, and I don't want to pay for something that still might not be of any use to me

Gemini 2.5 Pro Experimental (a frontier model) has 5 RPM and 25 RPD.

Gemini 2.5 Flash Preview 04-17 another powerful model has 10 and 500.

OpenAI also allows you to use their API for free if you agree to share the tokens.

Re: Show HN: I built an AI that turns GitHub codebases into easy tutorials

#160

Post by voidUpdate »

GaggiX wrote: post #159
voidUpdate wrote: post #158

Earlier quoted context omitted.

Well companies lock "frontier LLMs" behind paywalls, and I don't want to pay for something that still might not be of any use to me

Gemini 2.5 Pro Experimental (a frontier model) has 5 RPM and 25 RPD. Gemini 2.5 Flash Preview 04-17 another powerful model has 10 and 500. OpenAI also allows you to use their API for free if you agree to share the tokens.

What are "RPM" and "RPD"? I assume not Revolutions Per Minute?
Post reply on HN