I was unsatisfied with my browser options, I wrote my own and it does everything I need and I can modify it by "commanding" my agent to add/fix features. #melonbrowser
Reviewing civic duty done. Ready to take a good weekend break.
Checked my #opensource github issues/pull-requests. Heave, then -_-||| , and close laptop lid, I give up (for now)
#nlproc#llm#agenticnonsense
🚀 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!
github.com/Isalia20/metalBLA…
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.
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.
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.
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.
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.