A lot of this stems from friction in brittle process around applying edits or latency from full file rewrites.

The bar to beat is time it takes for human intelligence + Cursor Tab to complete a task, but in practice the bar becomes "feeling" like its faster

Notably missing fast apply like Morph

mcp is out! https://morphllm.com/mcp

I have never felt so disconnected from the findings of a study

Yeah, incremental updates are something models struggle with, which is what we're trying to solve.

for companies and startups we raise it considerably. For free tier there's rate limits + a limit of 100 req per month

This is a coding model, not a code merge model. What we do is 1 thing, extremely well - merging code edits into original files

we're quite a bit faster and specifically training for merging code edits.

Google diffusion is a swing at a generalist model. Super cool work nonetheless

Thats for 0 data retention - on the Morph website its: 0.80 /1M token input, $1.20 /1M token output. We have discounts for large volumes/reserved instances as well

yep - great post!