RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation · HackerPapers discussions

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation — mentioned by yogthos

Fri, 22 May 2026 16:39:17 GMT

My expectation is that local models will be the default for coding within a year or two. You can already run Qwen 3.6 with MTP at a pretty reasonable speed without needing a huge amount of VRAM. And while it's not as good as current frontier models, it's already quite competent for a lot of tasks. And there's no sign that people are running out of ideas for how to optimize models further. You see a bunch of papers come out literally every few weeks right now. So, it's entirely plausible to me that we'll see models that are superior to current frontier ones in a year or two that will run on…

Paper and discussion history. A mention is not an endorsement.

RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation — mentioned by yogthos

Fri, 15 May 2026 16:14:34 GMT

Here's a recent Stanford study showing that Chinese models are basically just as good https://hai.stanford.edu/news/inside-the-ai-index-12-takeawa... For most use cases, you don't actually need frontier performance either. Customization, cost, and data sovereignty are far bigger practical concerns. If you can run your own model on prem and tune it exactly what you need, then you're both saving money and getting better quality output. It's also wroth noting that tooling can go a long way to improve the quality of output from the models as well, and this is very much an under explored area…

Paper and discussion history. A mention is not an endorsement.