bhaktatejas922

psychologically bad for a person isn't grounds for something arising. I'm not arguing this should or shouldnt be morally, I'm just observing the situation. Utility to society doesnt alw…

most of the mechanisms you describe here are what is meant by "naturally arising"

it really matters when you care deeply about the product experience. The gap between something that works sometimes and something that works great everytime is what separated Cursor from the rest. Try…

yeah use ublock origin lite

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, …

Notably missing fast apply like Morph

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

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.

Im not sure that it's "better". I still use Opus and it's better at coding but needs more steering to be less of a "Yes you're EXACTLY right" every time i suggest a …

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

precisely. we work well on files up to 2k lines. It's hard to wrap your head around at first, but code merge has 100s of edge cases to deal with. Its the perfect application for a model

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

the claude link is hilarious, hahaha

What do we not complain about if we're being honest?

yep - great post!

if you make an account, we'll email you when we have something easier to try!

Claude Code uses find and replace, errors get piped back to the agent so you rarely feel them unless you hit an infinite error loop

say more! We're in the smart composer plugin, but the integration is out of date

thanks, let us know how it goes

Accuracy of course comes first - errors of any sort break flow state and are massively disruptive. Claude Code does search and replace. The failure rate of search and replace is rather high (over 11%…

if you've used cursor, you've probably felt how seamless fast apply can feel - fast apply is accurate and fast to the point where most don't even realize its a model

took a closer look, the update snippet provided is referencing css thats not defined. this is sort of a overreach example of the "semantic" nature of the edits - ie, if an update explicitly…

You should give both a try! key difference is our models are faster and more accurate by a large margin