morphllm's profile picture. ultra fast models that improve coding agents
10,500 tok/sec.
http://discord.gg/AdXta4yxEK

Morph

@morphllm

ultra fast models that improve coding agents 10,500 tok/sec. http://discord.gg/AdXta4yxEK

Pinned
morphllm's tweet image.

Morph reposted

gonna be posting some indepth evals super soon, but here's a teaser: - Stock Claude Code spent a minute on search, with warp grep it spent 14 seconds - Stock Claude Code injested 75k tokens, with warp grep it injested 3k - They both returned identical results (down to the line…

dhruvbhatia0's tweet image. gonna be posting some indepth evals super soon, but here's a teaser:

- Stock Claude Code spent a minute on search, with warp grep it spent 14 seconds
- Stock Claude Code injested 75k tokens, with warp grep it injested 3k
- They both returned identical results (down to the line…
dhruvbhatia0's tweet image. gonna be posting some indepth evals super soon, but here's a teaser:

- Stock Claude Code spent a minute on search, with warp grep it spent 14 seconds
- Stock Claude Code injested 75k tokens, with warp grep it injested 3k
- They both returned identical results (down to the line…

Introducing WarpGrep, a fast context subagent that improves coding agent performance. WarpGrep speeds up coding tasks 40% and reduces context rot by 70% on long horizon tasks by treating context retrieval as its own RL trained system. Inspired by Cognition’s SWE-Grep - we’re…



Morph reposted

I’ll be going over how we got sub 2s inference on ~90k code input (served on multiple b200s) in the next few days!

Introducing WarpGrep, a fast context subagent that improves coding agent performance. WarpGrep speeds up coding tasks 40% and reduces context rot by 70% on long horizon tasks by treating context retrieval as its own RL trained system. Inspired by Cognition’s SWE-Grep - we’re…



Morph reposted

Super hyped to ship this. RL is notoriously compute inefficient (even more so with MoEs), here's a thread on how we got around it

dhruvbhatia0's tweet image. Super hyped to ship this. RL is notoriously compute inefficient (even more so with MoEs), here's a thread on how we got around it

Introducing WarpGrep, a fast context subagent that improves coding agent performance. WarpGrep speeds up coding tasks 40% and reduces context rot by 70% on long horizon tasks by treating context retrieval as its own RL trained system. Inspired by Cognition’s SWE-Grep - we’re…



Morph reposted

Create your own "starter" version of Lovable in under 6 minutes. Here's how 👇 You'll need API keys/accounts with: - @firecrawl_dev - @GeminiApp - @vercel - @morphllm p.s. keys have been rotated :)

Introducing Open Lovable v3 - an open source AI design engineer 🔥 Enter a URL and agents will create an on brand clone you can build on top of. Powered by Gemini 3 Pro and @firecrawl_dev's new branding format. Try out the 100% open source example, link below!



Morph reposted

ty for @morphllm - it's fire


Morph reposted

The coding agent in Pilot generates the feature flag code along with the UI updates and uses @morphllm to apply the edits to your files. Super-quick and accurate.


In 2026, coding agents will go mainstream to the masses. This won’t mean everyone will be vibecoding. Sufficiently fast and good codegen is the new modality of creative expression. State, reactivity, and interactivity will make disposable codegen miniapps a pillar of online…


Morph reposted

4 horsemen of AI leaked

FlyaKiet's tweet image. 4 horsemen of AI leaked

English is the programming language of choice now

morphllm's tweet image. English is the programming language of choice now

You need both: grep for precision, semantic search for discovery The difference isn’t semantic search vs grep but it’s good semantic search vs lazy ones. Merkle trees, AST-aware chunking, custom embeddings, HNSW indexing is all built into Morph SDK npm install…

Semantic search improves our agent's accuracy across all frontier models, especially in large codebases where grep alone falls short. Learn more about our results and how we trained an embedding model for retrieving code.



United States Trends

Loading...

Something went wrong.


Something went wrong.