ONEKQ AI

company

AI & ML interests

Benchmark, Code Generation, LLM

Recent Activity

onekq  updated a collection about 2 hours ago
R1 Reproduction Works
onekq  updated a collection about 3 hours ago
R1 Reproduction Works
onekq  updated a collection about 3 hours ago
R1 Reproduction Works
View all activity

onekq-ai's activity

onekq 
posted an update about 2 hours ago
view post
Post
35
From my own experience these are the pain points for reasoning model adoption.

(1) expensive and even worse, slow, due to excessive token output. You need to 10x your max output length to avoid clipping the thinking process.

(2) you have to filter thinking tokens to retrieve the final output. For mature workflows, this means broad or deep refactoring.

1p vendors (open-source and proprietary) ease these pain points by manipulating their own models. But the problems are exposed when the reasoning model is hosted by 3p MaaS providers.