ensemblehq

4 bulan yang laludiscuss

Interested to keep updated on this point. As a consultant, I've worked on transformation of legacy applications so this would help me greatly as well. We've worked on pretty archaic systems where no one knows how the system works even if we have the source code.

ensemblehq

5 bulan yang laludiscuss

I can provide evidence for your claim. The technical debt can easily snowball if the review process is not stringent enough to keep out unnecessary functions.

ensemblehq

5 bulan yang laludiscuss

It’s going to be extremely difficult if PR and code reviews do not prune unnecessary functions. From what I’m experiencing now, there’s a lot of additional code that gets generated.

ensemblehq

5 bulan yang laludiscuss

This is exactly the issue I’m facing especially when working with AI-generated codebases.

Coding is significantly faster but my understanding of the system takes a lot longer because I’m having to merge my mental model with what was produced.

ensemblehq

6 bulan yang laludiscuss

There could be many factors at play here so it’s not clear what the main issue is. However, from experience, US VC funds typically come from other US institutions and so it’s an easier sell when the corporation is US-based. Rules and regulations are more well understood and less complex for funds. The article states the requirement is to flip the structure to have the parent company based in one of the 3 countries mentioned. Presumably, better business/returns/policies

ensemblehq

6 bulan yang laludiscuss

What’s missing from the writer’s analysis is also the desire from the population to create such businesses. Having lived in Asia for a bit, most of these small businesses are not wildly profitable and not everyone is willing to put in the hard work and effort to running these affordable restaurants.

ensemblehq

7 bulan yang laludiscuss

Have you tried using non-LLM based methods? Like starting with something rules-based and working through a layered multi-model setup?

That’s what we’ve been using for document extraction where accuracy needs precision (capital markets documents, medical assessments). We had a go at pure LLM with medical documents but the output was poor and felt like it would take substantial investment to create something more robust.

comments