News for hackers. Stuff that matters.
Re:The path to ubiquitous AI (17k tokens/sec) by gordonhart on Friday February 20, 2026 @01:13PM (#47091586)
We’re reaching a saturation threshold where older models are good enough for many tasks, certainly at 100x faster inference speeds. Llama3.1 8B might be a little too old to be directly useful for e.g. coding but it certainly gets the gears turning about what you could do with one Opus orchestrator and a few of these blazing fast minions to spit out boilerplate…

There are no comments on this comment yet.