Chris Levy (@cleavey1985) profile picture

DevRel @modal

Halifax, NS, Canada
Joined February 2013
Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)Photo by Chris Levy (@cleavey1985)
career update: I joined @modal this week to work on DevRel. Supper excited to keep building stuff with Modal. Thanks to @bernhardsson and @AAAzzam for the awesome opportunity! If your building on Modal or wondering where to get started, please reach out! More to come! 💚
21
6
1
145
8,437
In my first weeks at @modal, I've been spending more time in the platform and taking notes. I'm sharing some of what I've learned, along with the code, in two personal blog posts if you are interested in learning more. One post looks at how to turn a Sandbox into a Linux desktop, a browser, or an Android phone, and let a model drive it with a short agent loop. The only dependency is modal. drchrislevy.com/blog/modal-c… The other post explores some different patterns for creating agents using Sandboxes. Things like where the loop and tools run, credentials, sidecars, networking, and snapshots. drchrislevy.com/blog/modal-a…
10
11
76
4,657
And by using shared endpoints, usage is billed per token! modal.com/docs/guide/shared-… Get up and running in minutes 🚀
We Have the Models Kimi K3.1 Pro, DeepSeek V4.1 Flash 1017, GLM-5.3, Inkling 2 Small, and more, all running on @modal thanks to @Teknium for getting this in so quickly!
1
5
333
Super excited about this! I spent 6+ years on gVisor at Google, then recently joined Modal. It’s been an adventure pushing the frontier of gVisor’s capabilities and performance here. @modal is one of the most advanced gVisor users, running 40M+ containers a day, so we care a lot about where the project goes. Glad to see it move to CNCF, and happy to be back as a maintainer.
gVisor is joining the @CloudNativeFdn, and Modal is becoming one of its maintainers. We’ve run gVisor on Modal since day one. Along the way we've upstreamed: GPU support, multi-node training, snapshots, and more. All of it open-source. We’re incredibly proud to grow from being a team that depends on gVisor to a team that also gets to help steer it.
12
16
3
237
30,713
Great opportunity for builders to access compute and showcase their projects! 🚀
Compute shouldn’t be the bottleneck for your next big idea. We're launching Modal for Builders, a program that provides compute credits to builders working on ambitious AI projects. Have a demo you’ve been wanting to build? A research question you want to explore? Or another idea that needs compute? We’d like to hear about it. Apply with your idea and an estimate of the compute you’ll need. Projects may also be featured on Modal’s social channels. Some projects we’ve backed in the past:
8
509
Sharing a little weekend project of an app for training neural amp models on @modal For learning/capturing guitar tones 🎸 It’s using the NAM tech/library created by Steven Atkinson. Training a new tone for 400 epochs takes about 3½ minutes on an RTX PRO 6000, costing roughly US$0.30 per run including startup and idle overhead. Links in the thread below.
2
1
13
934
Would love for someone who’s tried this type of thing before to upload their input and output wav files to my temporary live Demo and try creating some tones! drchrislevy--neural-amp-mode…
1
68
Finally. I Love my @NeuralDSP quad cortex mini which I recently got. So good! I used it to power this investigation and create the sounds for training. @NeuralDSP , you should seriously check out @modal if you have not already, for training models 💚
271
Chris Levy retweeted
Introducing Isometric SF A pixel-art map of the entire SF Bay Area, over 1,300 square miles, all painted by Klein, a 4B-parameter image-to-image model, on @modal. Explore the map now! isometricsf.com
151
245
79
3,865
454,040
Chris Levy retweeted
nice guide on fine-tuning our d1-2B decision models with images
I saw @helloiamleonie’s recipe for fine-tuning a @LiquidAI decision model on text and wanted to try it with images too. Started with d1-3B but also added d1-2B as well, which was just released. Given a website screenshot, a task, and candidate page elements, the decision model selects which element to interact with next. After one epoch on Mind2Web, using one RTX PRO 6000 per model on @modal: • d1-3B: 44% → 91% accuracy, ~44 min training • d1-2B: 51% → 96% accuracy, ~20 min training I’ve shared the training, evaluation, and endpoint-serving code, plus a video walkthrough: drchrislevy.com/blog/liquid-…
2
8
110
5,500
I saw @helloiamleonie’s recipe for fine-tuning a @LiquidAI decision model on text and wanted to try it with images too. Started with d1-3B but also added d1-2B as well, which was just released. Given a website screenshot, a task, and candidate page elements, the decision model selects which element to interact with next. After one epoch on Mind2Web, using one RTX PRO 6000 per model on @modal: • d1-3B: 44% → 91% accuracy, ~44 min training • d1-2B: 51% → 96% accuracy, ~20 min training I’ve shared the training, evaluation, and endpoint-serving code, plus a video walkthrough: drchrislevy.com/blog/liquid-…
6
9
2
74
9,391
Chris Levy retweeted
my favorite bit of spindle is the flexibility - you can write your own code for model configs and even write fully custom execution backends! we specialize on orchestration and autoscaling; you get to focus on making your forward passes work exactly how you want
Tinker changed how people do post-training. We're big fans, and so are many of the teams we work with. But as those teams scale up, they keep raising the same two problems: per-token pricing gets expensive quickly, and you’re limited to the models and features the provider decides to support. We think a good API deserves more than one implementation. Today we're releasing Spindle, an open-source, Tinker-compatible training server that runs in your Modal workspace. Your existing Tinker scripts run unchanged, and because you own the server, you pay for GPU time instead of tokens.
2
2
30
2,004
Chris Levy retweeted
Tinker changed how people do post-training. We're big fans, and so are many of the teams we work with. But as those teams scale up, they keep raising the same two problems: per-token pricing gets expensive quickly, and you’re limited to the models and features the provider decides to support. We think a good API deserves more than one implementation. Today we're releasing Spindle, an open-source, Tinker-compatible training server that runs in your Modal workspace. Your existing Tinker scripts run unchanged, and because you own the server, you pay for GPU time instead of tokens.
14
34
22
583
75,911
Check it out! Learn about some cool use cases for one of Modals new primitives: Sidecars for Sandboxes.
7
824
Here’s the demo and talk I promised! Running Docker Compose apps, tests, and coding agents inside Modal VM Sandboxes. Video, slides, and code all here: drchrislevy.com/blog/modal-v…
I've been using Modal's vm sandboxes while they were in beta, and it's exciting to see them GA now. They are great for running traditional docker and docker-compose workloads. Will post a blog post soon and a video of a recent talk I gave on a specific use case.
1
7
1,800
I've been using Modal's vm sandboxes while they were in beta, and it's exciting to see them GA now. They are great for running traditional docker and docker-compose workloads. Will post a blog post soon and a video of a recent talk I gave on a specific use case.
Replying to @modal
VM Sandboxes give your agents access to a full Linux kernel. Reach for VMs when your agents reach the limits of limits of user space: working with Docker, FUSE filesystems, and certain Linux kernel features. modal.com/blog/vm-sandboxes-…
2
1
27
4,378
Chris Levy retweeted
Just launched at Modal Runtime: - Multi-node clusters - VM Sandboxes - Sandbox Sidecars - Sticky Sessions And more:
18
18
6
257
23,194