Top all-time · #283
Modular Blog
Company blog · modular.com/blogprogrammingai
Modular Blog is the company blog at modular.com, writing about programming and ai. Since 2022, 175 different Hacker News readers have linked it 261 times, most often “Mojo – a new programming language for AI developers”. It is still writing: the last post was on 2026-10-22, and you can follow it by feed.
The unified AI inference stack - from custom GPU kernels to production cloud serving on NVIDIA and AMD. 2x performance. Top open models. Open source stack.
Most-linked posts?
- Mojo – a new programming language for AI developers36 people · 39 mentions · first linked 2023-05-02
- The Claude C Compiler: What It Reveals About the Future of Software9 people · 11 mentions · first linked 2026-02-19
- Mojo: Programming Language for All of AI9 people · 9 mentions · first linked 2024-01-12
- Modular AI (Chris Lattner AI Startup)7 people · 7 mentions · first linked 2022-08-28
- Do LLMs eliminate the need for programming languages?7 people · 7 mentions · first linked 2023-06-08
- The fastest unified matrix multiplication6 people · 6 mentions · first linked 2023-04-20
- The Path to Mojo 1.05 people · 6 mentions · first linked 2025-12-05
- Democratizing AI Compute, Part 5: What about CUDA C++ alternatives?5 people · 5 mentions · first linked 2025-03-05
- What memory ownership is about: a mental model approach5 people · 5 mentions · first linked 2024-05-29
- The Next Big Step in Mojo Open Source5 people · 5 mentions · first linked 2024-03-28
What Hacker News says?
There's Mojo, but it's been a while since I've heard anything about it. https://www.modular.com/mojo
Comment linking /mojo
on “Uv is the best thing to happen to the Python ecosystem in a decade”Submitted Understanding SIMD: Infinite complexity of trivial problems as a story · 257 points
HN discussionThis kind of sound like Mojo. I wonder how these compare? (Besides HVM/Bend being opensource, which is awesome.) https://www.modular.com/max/mojo
Comment linking /max/mojo
on “Bend: a high-level language that runs on GPUs (via HVM2)”Submitted The Next Big Step in Mojo Open Source as a story · 162 points
HN discussionthe interesting comparison nowadays would be against mojo: https://www.modular.com/max/mojo
Comment linking /max/mojo
on “Bend: a high-level language that runs on GPUs (via HVM2)”Submitted Mojo – a new programming language for AI developers as a story · 86 points
HN discussionLattner left Apple a long while ago. He's been working on Mojo, a different (Pythonic) language and runtime: https://www.modular.com
Comment linking /
on “Apple is open sourcing Swift Build”Submitted Deep Dive into Ownership in Mojo as a story · 57 points
HN discussionLLVM people have been at it for a while now, they got it working on Nvidia and AMD working on apple I believe: https://www.modular.com/ it baffles me that more people haven't heard about them. it's mighty impressive what they have achieved.
Comment linking /
on “Rust running on every GPU”Submitted Mojo vs. Rust: is Mojo faster than Rust? as a story · 54 points
HN discussion> I'm still waiting on a Python project that compiles to pure C In case you haven't tried it yet, Pythran is an interesting one to play with: https://pythran.readthedocs.io Also, not compiling to C but to native code still would be Mojo: https://www.modular.com/max/mojo
Comment linking /max/mojo
on “Nvidia Warp: A Python framework for high performance GPU simulation and graphics”Submitted Outperforming Rust DNA sequence parsing benchmarks by 50% with Mojo as a story · 47 points
HN discussionMost of the stuff you pointed out is addressed in a series of blog posts by Lattner : https://www.modular.com/democratizing-ai-compute
Comment linking /democratizing-ai-compute
on “How China built its ‘Manhattan Project’ to rival the West in AI chips”Submitted Max GPU: A new GenAI native serving stac as a story · 40 points
HN discussionCuda is 20 years old and it shows. Time for a new language that fixes the 20 years of rough edges. The Guy (Lattner) who made LLVM is working on this: https://www.modular.com/mojo Good podcast on him: https://newsletter.pragmaticengineer.com/p/from-swift-to-moj...
Comment linking /mojo
on “How China built its ‘Manhattan Project’ to rival the West in AI chips”Submitted Modular and AMD: Unleashing AI Performance on AMD GPUs as a story · 33 points
HN discussion> Python is a poorly designed language by many accounts Hubris isn't rare. > what language has it significantly influenced? I can think of at least 1 language designer[1] who doesn't think it's "poorly designed," based on it's significant impact on what they're currently working on[2] 1. https://en.m.wikipedia.org/wiki/Chris_Lattner 2. https://www.modular.com/mojo
Comment linking /mojo
on “Everything you need to know about Python 3.13 – JIT and GIL went up the hill”Submitted Max Developer Edition Preview as a story · 27 points
HN discussionMojo from Modular? I've not checked it out enough yet, and it's early days for it anyway. Just saying it may be worth keeping an eye on. I've seen some videos of Chris Lattner talking about it. https://www.modular.com/mojo https://hn.algolia.com/?q=mojo
Comment linking /mojo
on “"We're building a new static type checker for Python"”Submitted Matmul on Blackwell: Part 2 – Using Hardware Features to Optimize Matmul as a story · 23 points
HN discussionTheir standard lib is in there, seems more open to me Theres the announcement where they open sourced the modules in their standard lib: https://www.modular.com/blog/the-next-big-step-in-mojo-open-... There's the standard lib: https://github.com/modularml/mojo/blob/nightly/stdlib/README...
Comment linking /blog/the-next-big-step-in-mojo-open-source
on “A 100x speedup with unsafe Python”Submitted Mojo: It’s Finally Here as a story · 22 points
HN discussionModular claims that it achieves 93% GPU utilization on AMD GPUs [1], official preview release coming early next year, we'll see. I must say I'm bullish because of feedback I've seen people give about the performance on Nvidia GPUs 1. https://www.modular.com/max
Comment linking /max
on “Making AMD GPUs competitive for LLM inference (2023)”Submitted Mojo is now open source! as a story · 21 points
HN discussionMojo no longer requires an account to install. But that is irrelevant to the conversation because this is not about Mojo but something they call MAX. [1] 1. https://www.modular.com/max
Comment linking /max
on “Making AMD GPUs competitive for LLM inference (2023)”Submitted Modular Raises $250M to Scale AI's Unified Compute Layer as a story · 17 points
HN discussionMaybe from Modular (the company Chris Lattner is working for). In this recent announcement they said they had achieved competitive ML performance… on NVIDIA GPUs, but with their own custom stack completely replacing CUDA. And they’re targeting AMD next. https://www.modular.com/blog/introducing-max-24-6-a-gpu-nati...
Comment linking /blog/introducing-max-24-6-a-gpu-native-generative-ai-platform
on “Making AMD GPUs competitive for LLM inference (2023)”Submitted CUDA is the incumbent, but is it any good? as a story · 17 points
HN discussionYou might also enjoy this series: https://www.modular.com/democratizing-ai-compute which goes into a lot of the details.
Comment linking /democratizing-ai-compute
on “ML needs a new programming language – Interview with Chris Lattner”Submitted Modular Raises $100M as a story · 12 points
HN discussion
