11–20 of 489 posts
Surely a company as large as Microsoft is actively attempting to build their own models. They couldn't possibly have expected to stake the future of their software development on the conditions of a third party company?
There are papers describing KV cache precomputation for commonly used documents (e.g. KVLink), but, of course, it's not a priority for model providers: they'd rather sell you more tokens, also they would rather get to AGI/ASI first than optimize usage of existing models...
There's definitely a way to use Claude code that is token conscious. I've tried throwing unsupervised agentic software factory workflows against the wall, and they burned through my tokens like nobody's business but didn't produce much. Supervised, human-in-the-loop process on the other hand is much more productive but doesn't consume nearly as much. Maybe that's why everyone's pushing agentic approaches so much.
Surely a company as large as Microsoft is actively attempting to build their own models. They couldn't possibly have expected to stake the future of their software development on the conditions of a third party company?
At one point there were rumours that they'd do that. They also have the rigts to oAI models for a few more years still, so they could always use that but apparently they're also compute starved (like anyone else).
There's definitely a way to use Claude code that is token conscious. I've tried throwing unsupervised agentic software factory workflows against the wall, and they burned through my tokens like nobody's business but didn't produce much. Supervised, human-in-the-loop process on the other hand is much more productive but doesn't consume nearly as much. Maybe that's why everyone's pushing agentic approaches so much.
I tend to work with the agent, and observe what's going on as well as review/test and work through results/changes. I spend a lot more time planning tasks/features than the execution, even using the agent as part of planning and pre-documentation. It works really well. I don't think people burning through the 5hr allotment in under an hour are actually reviewing/QC/QA the results of what they're doing in any meaningful way, and likely producing as much garbage as good (slop).
I'm really curious as to HOW the MS employees were using the agents as much as what they were doing.
There's definitely a way to use Claude code that is token conscious. I've tried throwing unsupervised agentic software factory workflows against the wall, and they burned through my tokens like nobody's business but didn't produce much. Supervised, human-in-the-loop process on the other hand is much more productive but doesn't consume nearly as much. Maybe that's why everyone's pushing agentic approaches so much.
Speed without judgement always compounds badly.
This is an AI generated summary of a blog post ( https://www.thelowdownblog.com/2026/05/microsoft-cancels-int... ) which is a summary of an AI generated article ( https://blazetrends.com/microsoft-cancels-claude-code-pilot-... ) which is a summary of another AI generated article ( https://www.themodelwire.com/article/microsoft-starts-cancel... ) which is a summary of an article from The Verge ( https://www.theverge.c…