The only thing this will achieve is making accurate, reliable information harder to find once the garbage it generates gets ingested by the other models.
I burned a ton of tokens this summer trying to document our legacy codebase in hopes of quantifying parts ahead of a refactor. My conclusion was that LLMs are bad at this. It waffled between unhelpfully verbose to omitting key aspects. I had to manually review each page. It really struggled with cross file references and inheritance. I tried several approaches, top down, bottom up, text first, diagram first. Maybe I'm not the prompt wizard I need to be. But I would never trust AI summary of any code longer than 500 lines.
It would be nice if the Google PM(s) and engineers attached to this project were well-versed enough in searching the Web to be able to turn up the definition for the word "wiki". Instead, because these fucking dipshits couldn't spend two goddamn seconds (dis)confirming their hunch that it means more or less the same thing as "encyclopedia" or "knowledgebase", they vomit this bullshit out into the universe and encourage everyone else to treat the words as interchangeable, too.
Fuck everyone associated with this.
Surprising that they haven't made a podcast (NotebookLM-esque) based on the repo - that one can listen to on a bus ride. Something I had created a while back https://gitpodcast.com
Nice! I've been using deepwiki and loving it! Obviously goggle's gemini powered alternative would be much better and trustworthy.
I just hope Google doesn't kill this one as quickly as they did Stadia etc.
Previously: https://news.ycombinator.com/item?id=45926350
I hoped this might be like an externalization of g3doc. Nope.
Instead, I started reading through one of their highlighted examples --- the Go repo (https://codewiki.google/github.com/golang/go). This might be the worst high level overview of Go and its repo I've read. Mostly accurate but unhelpfully verbose, spending lots of words on trivia, and not at all making a compelling pitch for Go as a language or toolchain, how to use it, or how to work on it.
Realistically, the alternative to code wiki is not good documentation, it's no documentation.
How does it know about the tradeoffs and discussions imbued in the code, unless someone has already put it in writing?
This is really terrible. My brain instantly goes on standby trying to read any of this walls of text.
I've seen a few of this type of thing pop up in search results ("DeepWiki" by Cognition.) I'm not a fan. It is just LLM contentslop, basically. Actual wikis written by humans are made of actual insight from developers and consumers. "We intend you use it in X way", "If you encounter Y issue, do Z." etc. Look at arch wiki. Peak wiki-style documentation, LLMs could never recreate. Well, maybe with a future iteration of the technology they can be useful. But for now, you do not gain much by essentially restating code, API interfaces, and tests in prose. They take up space from legitimate documentation and developer instruction in search results.