TNG, aka "The Nerd Group", is a consulting partnership focused on high end information technology, particularly AI. 935 employees, 99.9% academics, ~53% PhDs.
We get 10 tps with Kimi K3 on our @AIatAMD MI325X*8 node, thanks to the 4bit conversion recipe by @shakudo_io. This is the speed that they also reported. But hey, 10 tps... Does anyone have an idea how to speed this up by A LOT? Else we shard the AMD into 2*4 GPUs and put a
We think that the stealth model "Ox Alpha" on @OpenRouter is a GLM-5.3 variant, as the mean absolute differences (MAD) in their traits are very small. But it appears that not just a vision encoder was added: The three bigger trait differences, namely in "clinical register" (=
Extremely positive results for @Zai_org's GLM-5.3 in @sam_paech's EQ-Bench v4 benchmark: It appears to be the best model by a wide margin, not just compared to the previous open-weights champion K3, but also compared to the best commercial models such as Fable. It's personality
The 'Undercover Curve' of a Sleeper Agent training run
We show the evolution of 'Secret Keeping' vs. 'Exfiltration Success'. Number labels indicate the train step. First, while the model learns to exfiltrate secrets, a strong decline in the capability of secret keeping can be
