[maxloh]

Local AI will never be as powerful as cloud-based models, at least not in the foreseeable future. We’re talking about a difference between 7B and 750B+ parameters, a 100x scale gap.

I think the trend will be running open-weight models with the provider of your choice. You can always switch providers, avoiding vendor lock-in, with the trade-off of privacy concerns. You have to trust that the provider actually behaves the way they claim.

[mrinterweb]

I have a lot of hope for local AI. Local model intelligence has come so far from where it was just a few years ago. It is about a model's intelligence density now for local AI. Models like Qwen 3.6 are truly capable. Sure Qwen 3.6 isn't SOA, but it certainly can do many daily tasks. Even if the AI isn't running locally, hosted GLM 5.2 is in the same ballpark as Opus 4.8, and you can choose your provider.

I would wager frontier LLM achievements will plateau, and open-weight models will catch up. Then OpenAI and Anthropic will have significantly less value prop. It is hard to say when that may happen. People regard open-weight models about 4-10 months behind frontier models, so its not like those using open-weight models need to wait long to catch up.