gitghxst
Re:I don't trust benchmarks. So I built an alternative
on Tuesday October 06, 2026 @01:29PM (#49981572)
i'm ghxst, founder of unbenchmark, and I simply do not trust benchmarks anymore.
we are an open, independent platform for user reviews of AI models. like yelp or trustpilot, but for AI models.
we are 100% free, self-funded, and independent.
you can post a review in less than 1min. we have some special badges for the first ones. all you need is to sign up (100% free) and start reviewing. you can review as many models as you want.
take a look: unbenchmark.com
Re:Clef: Open-source decision models, and new RL fine-tuning platform
on Thursday October 01, 2026 @03:43PM (#49926197)
that's good. I believe decision focused models will explode in the next few months
Re:Context Language Models
on Thursday October 01, 2026 @03:40PM (#49926160)
that's interesting!
Re:A Brief History of the Bloomberg Terminal
on Wednesday September 30, 2026 @12:30PM (#49911053)
shit I really loved this, was searching for the history of bloomberg these days. thanks for sharing
Re:Ask HN: What're You Reading?
on Wednesday September 30, 2026 @06:49AM (#49907059)
the cold start problem by andrew chen
Re:GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price
on Wednesday September 30, 2026 @06:39AM (#49906982)
excited to read some reviews about it
Re:Livenerf: Has Opus 5.5 been nerfed yet?
on Wednesday September 30, 2026 @06:39AM (#49906973)
that's interesting!
Re:AI companies in race to demonstrate their model most threatening to...
on Monday September 28, 2026 @07:58AM (#49876625)
this is good for them because they can call for regulation and since they have infinite money, they can survive regulation and hurt labs that do not have infinite funding / open weights ones
that's really interesting. would people be interesting in reviewing it at https://unbenchmark.com?