Morph
@morph_labs
Followers
5K
Following
13
Statuses
36
Imagine if you could: Create instant parallel versions of a running cloud computer with zero overhead Explore millions of reasoning paths forward with AI agents simultaneously And do it all in a fraction of a second Today, we're announcing Infinibranch.
6
25
157
happy new year! excited to share some of our recent work @morph_labs we're building infra for agents to run in secure sandboxes and scale test-time compute demo below: taking a full snapshot of a failed ci test and jumping into a debugger from the point of failure to fix it
0
0
11
RT @abetlen: happy new year! excited to share some of our recent work @morph_labs we're building infra for agents to run in secure sandbox…
0
3
0
btw using MorphVM snapshots we can run the entire SWEbench eval harness in 30 seconds using 10X less space than the official docker images. email or dm if you're building AI SWE agents and want to try
Imagine if you could: Create instant parallel versions of a running cloud computer with zero overhead Explore millions of reasoning paths forward with AI agents simultaneously And do it all in a fraction of a second Today, we're announcing Infinibranch.
1
3
28
RT @morph_labs: Imagine if you could: Create instant parallel versions of a running cloud computer with zero overhead Explore millions of…
0
25
0
RT @jessemhan: this one is a personal favorite - playing chess in a browser on a MorphVM against Claude. when Claude makes a move we don't…
0
4
0
RT @jessemhan: this is super useful for computer using agent R&D. for example, we can record and timetravel instantly to the exact VM state…
0
4
0
RT @jessemhan: Excited to unveil Infinibranch — infrastructure for scaling test-time search with the next billion autonomous SWEs. Morph In…
0
7
0
Morph Infinibranch VMs are infinitely scalable and instantaneously branchable ephemeral AI devboxes custom-built for scaling test-time search with computer-using agents. Read more: Get early access:
0
1
18
RT @jessemhan: i am hiring a full-time research engineer to work on creating superhuman quality synthetic data for evaluating and post-trai…
0
5
0
Automated evals like ours enable faster development of AI coding systems while addressing the high cost of manually curating benchmarks of questions over diverse codebases:
0
0
2
Customer highlight: congrats @StoriaAI on this dataset release! This data was generated with our automated codebase-specific eval platform at 25X lower cost and 10X faster than other leading data providers.
Tired of building AI coding agents based on vibes? Together with our friends from @morph_labs we made a real-world dataset that gives us a ladder to climb: 1,000 questions about the Transformers library. Here are our initial learnings about proprietary APIs. 🧵
1
0
5