First tests of running a local LLM - Ollama, Jetbrains Webstorm
Loaded up qwen3.8:latest
Huge waiting times on each query. Granted, it's "Gathering Context" but still, pretty slow.
My system is an AMD Ryzen 7 9800 x3d, RX 9070 XT, 32 GB RAM.
Possibly VRAM issue. Still digging
@TasonJorres Hey Jason! Thanks for asking. I don't think it's the IDE because it's the same behavior in VS Code.
I definitely suspect Ollama eating up resources, will try llama.cpp first.
Ran some refactoring suggestion queries with Qwen3.8 LLM running locally and it's pretty great, after the way too long wait.
Looking into what drags the whole thing.
I've installed @pewdiepie 's Odysseus with Qwen Code. Pretty slick, having lots of fun with the whole setup.
Odysseus seems to be a slick UI contextual wrapper for running the LLM. Definitely makes some things easier.
After 18 years of using Visual Studio for C# I might actually switch to Rider.
Also webstorm is awesome. I'm starting to really dig the @jetbrains suite.
Honestly, I think when it comes to guitar instructors, Paul Gilbert might be the best of all time. The G.O.A.T.
Been practicing his speed lick ideas with string skipping and it really opens doors left and right.
Wow - a vulnerability was found in Cursor’s CLI agent, which permitted a cloned repository to execute arbitrary commands without asking for permission. That's pretty wild.
Cursor patched the behavior quickly. It's great that they're so responsive.
@elonmusk How about, after finishing a task, it could also include architectural design suggestions in the summary of done work e.g. design patterns, separation of concerns, potential refactors, scalability notes, or cleaner structure recommendations 😎
Terafab will be built in Grimes County, Texas
In April, we broke ground on our research fab on the North Campus of Giga Texas – the precursor to Terafab.
Both Tesla & SpaceX will need far more chips than current & future global production can supply.
This is why we're building the largest chip manufacturing facility ever, with the goal of producing over 1 terawatt of compute per year
The future is built in Texas
https://t.co/RQPNlAasdP