VibeThinker: 3B param model that beats Opus 4.5 on reasoning with novel SFT+GRPO

Re:VibeThinker: 3B param model that beats Opus 4.5 on reason... by j45 on Tuesday June 23, 2026 @09:05AM (#48644397)

It feels sometimes like optimizations are only starting.

[ Parent | on HN ]

Re:VibeThinker: 3B param model that beats Opus 4.5 on reason... by trollbridge on Tuesday June 23, 2026 @10:12AM (#48645287)

I’m beginning to suspect the closed SOTA labs were doing all these optimisations, keeping quiet about it, and just charging us out the yinyang for inference.

[ Parent | on HN ]

Re:VibeThinker: 3B param model that beats Opus 4.5 on reason... by j45 on Wednesday June 24, 2026 @01:36PM (#48663183)

Also as much landgrab as possible for data centres, infrastructure, that can kepe it running for the next 5-15 years.

Why does an M1 Max continue to remain capable, if not more capable with every passing year with LM Studio? :)

[ Parent | on HN ]