calumcl

There's even less of a place for it considering the Opus price drop as well, I'll still try it but I see no reason to not just do Opus Low/Med instead.

Interested to see if new Haiku gets a big price drop and is comparable to Luna, Haiku is just incredibly out of date with current basement bin pricing.

There was context for neither in your original post and I personally saw a lot of similar takes like the above online - apologies for the misunderstanding. I personally thought it was pretty clear considering the parent link is a link to the API pricing and their public communication on their twitter/blogs were "Subscription usage remains unchanged".

Subscribers were already getting subsidised compute and value compared to the 20-200$ fee, peak cakeism to want more considering the alternative would likely be consumption based pricing for individuals so you "benefit" from OpenAI giving up some of their markup (and heavy users end up SOL).

They've provided a skill with their stacking CLI to provide guidance to any coding agent and the Copilot harness now ships with a pr-stack command to do exactly what you're saying for PR splitting FYI: https://twitter.com/_JeremyMoseley/status/208219039710799469...

The maintainer works on mlx-vlm so he does have pedigree in the scene, I'm don't know if this is just going to end up as unmaintained slop. I haven't tried this but I would personally just recommend oMLX for a currently more complete and fleshed out package - loads of features, provides the same MLX support and changelogs + commits are actually detailed.

You could easily just use Pi or even a Codex fork to avoid Opencode as a harness and still pay zero dollars.

Databricks wouldn't be using a subscription plan though due to the size of their engineering team which is what matters here. Free lunch is over for basically all providers' biz coding plans

> These models are hosted on US-based Azure AI Foundry infrastructure managed by GitHub and Microsoft. Customer prompts and responses are not sent to the original model developers.

From your link: https://docs.github.com/en/copilot/reference/ai-models/model....

This is a job for a charity - you're never getting stock + bonuses + competitive pay in a third sector job. UK pay is not near US but this is probably still median SWE pay outside tech roles and London + FAANG + others will pay closer with what you're suggesting with the mentioned bonuses/stock.

Red and Blue are the international releases of Gen 1 that came out about 2 years after Red/Green.