not impressed with their PR security review bot, vanilla GLM 5.3 flash finds more
it also has too many false positives
> We achieved a total 78.2% model size reduction compared with GLM 5.3 at full precision, and a 32.8% reduction compared with GLM 5.3 with an AWQ INT4 quantization. Altar retains 168 of the original 256 routed experts in each backbone expert layer, removing 88, or 34.4% of them. The router still selects eight per token, now from the smaller bank.
Looks like GLM based
not impressed with their PR security review bot, vanilla GLM 5.3 flash finds more
it also has too many false positives
> We achieved a total 78.2% model size reduction compared with GLM 5.3 at full precision, and a 32.8% reduction compared with GLM 5.3 with an AWQ INT4 quantization. Altar retains 168 of the original 256 routed experts in each backbone expert layer, removing 88, or 34.4% of them. The router still selects eight per token, now from the smaller bank.
This might explain it
[dead]