Beni’s all-terrain camera robot and OpenAI’s rumoured portable AI speaker point toward the same wonderfully obvious idea: a companion that follows you.
There is a very particular kind of future gadget that, once you see it, makes everything else look strangely stationary.
Nobody wants to be a model selector.
Most people do not want to decide whether a task deserves Fable, Sol, Opus, Sonnet or Haiku. They want the job done properly, quickly and without the invoice arriving as a small technical mystery.
That is where Token Blending comes in.
The idea is straightforward. Start an agentic task with the biggest, smartest and most expensive model. Let it understand the problem, make the difficult calls and create the plan. Then hand the defined work to a cheaper, faster model to execute.
The same code file now costs 30% more to process than it did three months ago. The price per token didn’t change. The tokenizer did.
Anthropic’s post-4.6 models - Sonnet 5, Opus 4.8, Fable 5 - use a new tokenizer that cuts text into more pieces than the 4.6 generation did, and you pay per piece. A detailed analysis by Playcode, who measured every frontier tokenizer on identical files, found the new Anthropic tokenizer produces 1.36 to 1.73 times GPT’s token count on the same content. TypeScript is the worst case at 1.73x.
How is it that Aesop figured this out 2,600 years ago but this wisdom is ignored in favour of “Greed is Good II”?
A CERTAIN MAN had the good fortune to possess a Goose that laid him a Golden Egg every day. But dissatisfied with so slow an income, and thinking to seize the whole treasure at once, he killed the Goose, and cutting her open, found her - just what any other goose would be!
Moral: Much wants more, and loses all.
Aesop 620 B.C. - 560 B.C.
Source: Aesop’s Fables Copyright 1881 WM. L. Allison, New York
Can’t remember where I first spotted this image. It makes a good point.
Thanks to the all powerful YouTube algorithms I was presented with this “Final Farewell” video from a now-deceased Irishman. I could see he was a very active Youtuber - 745 videos produced from 23 Mar 2018. Guess he lived some of his final days through YouTube presence, so naturally he thought he should end them there. His life. His choice. I hope his end was peaceful. Sounds like he’d been quite unwell.
A chart that shows OpenAI always ahead of Anthropic - or does it? #whenchartslie
As OpenAI try to move forward their models and apps they’re creating quite the muddle. My impression is that OpenAI are trying to do too much, too fast and in the process burning their users.