we've faced this same problem but thinking about it a little deeper reminded me that this issue is no different to pre-llm world. someone creates a spec, someone or a team build/implement the spec and after actioning any feedback from testing or from customers, the product evolves and is no longer aligned with the initial spec.
i think one way to solve this is having an someone or an agent update the initial spec with any new changes as and when they are made.
I’ve seen at least one person where I work doing this. They have an agent doing massive updates on Confluence constantly. It seems like a mess. It checks the box for having documentation, if that’s all anyone cares about. But there is no way people are actually reading it, looking for changes is impossible, since the LLM re-writes the entire page every time, and even not knowing their project well, it was full of hallucinations and nonsense.
If the LLM is going to write the doc anyway, why not just do it on demand from the code if/when it’s needed, instead of burning tokens on documents that no one will ever read?
I also think a lot of the value in those historical docs are the reasons why certain decisions were made, as it can be important context if there is every a discussion on doing things differently. The LLM likely won’t have that information, or may just make up a bunch of reasons the business doesn’t actually care about.
> What is also interesting is that London's productivity growth is falling compared to Manchester, Leeds and Liverpool. So those cities that aren't getting the fancy new train lines are actually performing better.
It's based on the Centre for Cities report: "How productive are the UK's big cities?" which mentions Liverpool's, Leed's and Manchester's productivity growth and The State of London Report 2025 which reports London's productivity decline
Product is very rarely the moat. It also depends on what you're building. A software startup can not win solely by just having a great product (of course there are exceptions). Finding a niche community, being able to distribute your product to them, how you price it, frequency of updates etc... all things that were just as important in building a moat pre agentic coding
" then open up the links having a high number of comments or sometimes, the ones whose titles intrigue me. Roughly, this would lead to opening about 5-6 web links per HN visit. For 3-4 of those, I’d return to their respective HN posts to read the comments. I usually browse up to the 2nd, and sometimes 3rd page of HN per visit"
I have used hn like this for last 10years - is this a thing that I'm not aware of?
reply