Liling Tan

Code, geek, game

[Liling Tan @alvations]

@lauriewired And the video: https://t.co/laa7NCIkaM

[Liling Tan @alvations]

Learnt some fun computing history from @lauriewired =)

Makes you wonder #llm https://t.co/TKvKq1hHeM

And also https://t.co/sLeZKp3vrH has a fun website.

[Isalia20 @Is36E]

🚀 open sourced metalBLAS, hand-tuned Metal matmul kernels for Apple Silicon, callable from PyTorch on mps.

Matches/beats MPS Graph (torch) matmuls on bf16/fp16, 2-3x faster on fp32 (TF32-relaxed) across the bench suite on M5 Pro.

Next step is to upstream this to PyTorch!
https://t.co/EMGdZaagXP

[Liling Tan @alvations]

And this makes it an even more attractive idea to pursue! 😊

[Liling Tan @alvations]

Apparently this is a wild enough idea that people are saying it sounds ridiculous but we’re not questioning pseudo #opensource translucent “open weights” #llm though they’re also binaries that generates code then the code generates the results.

[Liling Tan @alvations]

What if, #llm coding agents don't need to write human readable code, no #Python, no #Java, no C++, no cobol, just binaries. Binaries that we don't understand but the CLI does the job we need. The ultimate source, not closed source, #opensource but pure binaries.

[Liling Tan @alvations]

Okay, now lets think carefully (as if I'm prompting an #llm LOL), wouldn't any arguments saying that such a binary cannot be governed or audited or checked or reliable, doesn't the same applies to any "open weights" models?

#foodforthought for the weekend.

[Liling Tan @alvations]

What if, #llm coding agents don't need to write human readable code, no #Python, no #Java, no C++, no cobol, just binaries. Binaries that we don't understand but the CLI does the job we need. The ultimate source, not closed source, #opensource but pure binaries.

[Liling Tan @alvations]

https://t.co/HKQzrvzdKp 🤔

[Liling Tan @alvations]

With all these agents / #llm models in the wild. The true value will be created when human connection is placed first.

The barista that makes the coffee with a robot but talks to you while the robot is making it or fetching it from the preorder rack.

[Liling Tan @alvations]

合久必分 era should be over, 分久必合 is next and remember 世事變化無常

[Liling Tan @alvations]

Startup labs doing #llm should start doing mergers and acquisitions. What’s coming is going to wipe out a lot of high burn rate companies…

Think how much more powerful it’ll be if talent, compute and data is consolidated across these labs 😏

[Stanford NLP Group @stanfordnlp]

Many roughly know how a transformer works

To REALLY understand modern neural LMs—MoEs, GPU tiling, kernels, RLHF, data—you need CS336

By @tatsu_hashimoto, @percyliang

The 2026 edition appears on yt with ~2 weeks delay
https://t.co/iEWTqEivvB

Materials
https://t.co/E1pzUSC6Tr

[Liling Tan @alvations]

@MIT_CSAIL They can only spend money, not make them. What should happen is that agents should make money by themselves and make them self-sustaining.

If it’s really so useful and clever we shouldn’t need to pay subscription for it, it should go find money to pay for itself 😉

[Liling Tan @alvations]

254K -_- https://t.co/a4qH9G7P4Z

Okay, I give up...

[Liling Tan @alvations]

When stressed, build stuff =)
https://t.co/RisGfOoK9U

[Liling Tan @alvations]

And this person hunted some of them down... https://t.co/120G0TDTFj

[Liling Tan @alvations]

https://t.co/Zsls3giWtM

[hardmaru @hardmaru]

The human brain🧠 is incredibly efficient because it only activates the specific neurons needed for a thought. Modern LLMs naturally try to do this too (> 95% of neurons in feedforward layers stay silent for any given word), but our hardware punishes them for it.

One of the most frustrating paradoxes in deep learning: making a model do less math often makes it run slower. Why? Because unstructured sparsity introduces irregular memory access, and GPUs are built for predictable, dense blocks of math.

We teamed up with @NVIDIA to try to fix this hardware mismatch. Instead of forcing the GPU to adapt to the sparsity, we built a "Hybrid" format that reshapes the sparsity to fit the GPU. Our sparsity format (TwELL) dynamically routes the 99% of highly sparse tokens through a fast path, and uses a dense backup matrix as a safety valve for the rare, heavy tokens.

Through TwELL and a new set of custom CUDA kernels for both LLM inference and training, we translated theoretical sparsity into actual wall-clock speedups: >20% faster training and inference on H100 GPUs, while also cutting energy consumption and memory requirements.

Paper: https://t.co/rqIY9SYBDe
Blog: https://t.co/oRjNbpJKha
Code: https://t.co/FAFaJwpxAJ
⚡️