OpenAI JalapeñO: Better Than Nvidia Blackwell

Re:OpenAI JalapeñO: Better Than Nvidia Blackwell by cmrdporcupine on Tuesday August 25, 2026 @06:17PM (#49441441)

Right, I can do the talked about ~3 tok/sec output and drive a car, hold my bladder, and eat chips at the same time.

Take that, Jalapeno!

[ Parent | on HN ]

Re:OpenAI JalapeñO: Better Than Nvidia Blackwell by falcor84 on Tuesday August 25, 2026 @08:10PM (#49442507)

For what it's worth, LLMs don't really suffer from incontinence, so at least that part is pretty much a solved problem.

[ Parent | on HN ]

Re:OpenAI JalapeñO: Better Than Nvidia Blackwell by pantalaimon on Tuesday August 25, 2026 @08:33PM (#49442684)

They sometimes leak their system prompt

[ Parent | on HN ]

Re:OpenAI JalapeñO: Better Than Nvidia Blackwell by undersuit on Tuesday August 25, 2026 @09:47PM (#49443191)

So why are their water cooling systems filled with leak detectors? /s

[ Parent | on HN ]

Re:OpenAI JalapeñO: Better Than Nvidia Blackwell by desterothx on Friday August 28, 2026 @10:27AM (#49479017)

Also, I can talk at a lot more than 3 tok/sec, its just going to be more gibberish (see thinking traces)

[ Parent | on HN ]