@ivanfioravanti SPOILER: Open Weight models of more than 2 trillion of parameters will be banned in US. It will be authorized only for autonomous drive systems.
@antirez@kai_fell I can confirm that the Vector Set implementation developed by @antirez in Redis is one of the fastest HNSW implementations out there. Now he's asking us to elevate our point of view. LbnL ... have you heard about Dwarf Star? They say its implementation was overlooked by a clown.
@Youssofal_@ivanfioravanti what is :
"Drafted / verify call
0.00tok/call
0 drafted · 1,071 verifies"
in my M4Pro is always zero, but i can guarantee that old fused kernels drive Qwen 3.6 35B A3B so well that has never been so fast (without losing smartness , in comparison to unsloth 6b XL )
Fable still isn’t back (sad). GLM-5.2, meanwhile, is getting seriously good.
If Fable or GPT-5.6 can’t be released due to safety risks, and Kimi K3 or GLM-5.3 drops first, OSS LLMs may have a shot at beating publicly available closed-source models.
@antirez in real life "replying to affirmations with a vague remark of what the affirmation expressed" has happened since the years were with negative numbers