MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

Re:MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per s... by andai on Monday June 08, 2026 @07:57PM (#48454176)

I heard an anecdote. Guy spent several days trying to convince his AI agent to build a feature. Kept saying it was crazy complicated, would take weeks.

Finally he convinced it to try. It one shotted it in 30 seconds.

Turns out the agents' idea of what is hard and easy also comes from Common Crawl.

[ Parent | on HN ]

Re:MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per s... by wild_egg on Monday June 08, 2026 @08:04PM (#48454239)

Why on earth would you spend any time at all convincing an agent of anything? You say "just do it" and off it goes.

[ Parent | on HN ]

Re:MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per s... by dr_dshiv on Monday June 08, 2026 @08:17PM (#48454387)

Ya, but “doit” is 2x more efficient

[ Parent | on HN ]

Re:MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per s... by brianwawok on Monday June 08, 2026 @11:00PM (#48455751)

Uh Claude tries real hard to dodge work. Talks about how it’s really hard 10 PRs. Finally convince it to do as 1. It stops 10% through and says ok done with PR 1, we can work on the last 9 tomorrow. Ugh.

[ Parent | on HN ]

Re:MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per s... by g8oz on Tuesday June 09, 2026 @11:20AM (#48462282)

You need to assert dominance.

[ Parent | on HN ]

Re:MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per s... by handfuloflight on Tuesday June 09, 2026 @12:31PM (#48463323)

Maybe we shouldn't have AI mimic humans too closely?

[ Parent | on HN ]