dsrtslnd23
Joined 3 years ago
Karma
248
Submissions
127
Member since
May 7
Recent submissions
Comment · 1 month ago
same. built custom harness based on pi.dev and it works great for me with all providers.
Comment · 1 month ago
252GB of HBM3e at 100k vs. a multi A6000 96GB setup.
GB300 seem expensive in comparison at ~$100k. Am I missing something?
Comment · 1 month ago
are we sure humans have that choice?
Comment · 1 month ago
I also built a custom harness tailored to my needs using pi.dev underneath. From time to time I use the 'official' harnesses of openai/anthropic but can't confirm that they are much better adapted to that harness.
Comment · 1 month ago
exactly - this should be trivial.
Comment · 2 months ago
yes would also be interested in that - using knowledge distillation and other special knowledge sources to post-train on top of an open model like GLM-5.3. I was wondering that when Elon Musk tweeted "Specialist AI’s (single language, single area of knowledge) are another 100X" (src: https://x.com/elonmusk/status/2089968914596045178) - maybe he knows something regarding specialist model training the general public does not know?
Comment · 2 months ago
I think it really depends - for a lot of things outside of coding and general knowledge tasks even the best models (fable 5 etc.) are not good enough yet: e.g. CAD, PCB design (though getting there on PCB design), ...
Comment · 2 months ago
will this be open weights?
Comment · 2 months ago
I hear that often but to me it does not feel like it. I built my own framework around pi.dev harness and run all kind of different LLMs with it. Sometimes also use the vendor harnesses and they don't feel better adapted.
Comment · 3 months ago
maybe a quantized version on a GB300 would work? unsloth hopefully working on it.
Comment · 3 months ago
Seems that this will not be open weights?