Local AI @jetbrains | prev. astrophysics @ JetBrains Research | opinions are my own
Cyprus
- Tweets 4,557
- Following 221
- Followers 961
- Likes 23,285
Norm MacDonald would’ve turned 67 today
OTD in 1959, the one and only @normmacdonald was born. In his 61 years, he became one of the greatest comedians of his era, including as the anchor on @SNLUpdate and through standup. Below, one of the greatest jokes he ever did (on @ConanOBrien’s show).
1
138
I’m already working on more optimizations and custom models for @NVIDIARTXSpark
Local inference is so fun and full of ideas to be implemented
Junie Local now runs on @NVIDIARTXSpark from day one.
Get a full-fledged coding agent on your PC. It reads your code, edits files, and runs tests. There are no tokens or quotas, and no code leaves the machine.
Windows support is stable, too. All you need is a 24 GB Nvidia RTX card.
Try it for free: junie.jetbrains.com/local
ALT Image with a black background features text: "Your RTX Spark just got an agent. Junie Local runs on it from day one." The text is in white and green. The top corners display the logos for Junie and JetBrains. The bottom shows a green command line: "> /local".
2
8
205
Thank you @NVIDIAAI for giving us the opportunity to bring day-one support for @junie_ai Local on @NVIDIARTXSpark!
What I personally like the most about RTX Spark is that provides enough memory to run BOTH local AI experiments and local coding agents at the same time, all using the same CUDA stack that I use in prod
Here’s a screenshot of me asking Junie Local to run an SLM pretrain experiment - both are running on the same RTX Spark!
NVIDIA RTX Spark is here.
Build AI locally, bring your creative ideas to life, and take your favorite games along.
A new beginning for @Windows PCs starts today.
1
2
11
404
My first hand experience:
1) Roblox Studio’s MCP is really good
2) Rivals and steal an egg are fun af but blox fruits is a bit boring compared to WoW WotLK
Here are the current top earning Roblox games.
Nearly all use both AI coding + AI asset generation.
In some cases these games are entirely AI assets, not just one.
The top 20 games on Roblox collectively earn $8M A DAY.
There are hundreds of millions of people playing these games, and millions spending daily.
So the answer to who is paying for AI assets is very clear: the generation replacing us as gamers.
1
2
220
They noticed that block scales are 1 byte each but 99%+ scales within one row are actually just a few bits apart!
So they compress those scales, and the rest <1% of scales is still stored in full quality, at expense of 4 extra bits
It saves 45-48% storage per expert matrix!
Well what do we have here. Interesting new NVFP4 technique out of NVIDIA.
Here’s one for Qwen
huggingface.co/nvidia/Qwen3.…
1
5
513
>Interesting — GLM-5.3 is real (in this environment's world, dated 2026).
I call this reverse gaslighting
2
149
Dimuon is a new optimizer we built for LoRA fine-tuning. In our SFT tests, it often reaches lower loss in fewer steps than AdamW. We're still experimenting with Dimuon; you can Tinker with it today and share your feedback!
See our optimizers guide at tinker-docs.thinkingmachines…
1
117
A perfect local inference engine should have:
Drafters as first class citizens on decode path
SOTA expert offloading / streaming magic
Megakernels for dynamically quantized models with complex datashapes
Scheduler optimized for bs<=4
Different memory strategies for unified vs hierarchical memory - or even supporting only one of those
Power saving / low-TDP mode
From what I see, all popular inference engines right now only cover 1-2 of these at a time.
Would be cool if someone would bring them all together… right?
1
7
282
Should I go and disassemble my @ledger and check if there’s a spy antenna inside?
100%
Yes
0%
No
0%
No (I’m from DPRK)
10 votes • Final results
2
208
>ask codex to delete a nonsensical test it added earlier
>codex added a test that nonsensical test stays deleted
Smdh
4
164
