Hard to disagree: High token spend is generally a sign of unfocused work. One exception might be running auto-optimization systems, but even then there are cost-efficient ways to do it. Different workflows have different price/convenience tradeoffs.
Jeff Preshing
@preshing
Canadian software developer
- I love a good bargain.Here’s a fun comparison between GLM 5.2 and Opus 4.8 on a one-shot reproduction of the SDPO paper This is a hard task: the model must resolve messy verl issues and then run ablations to completion and confirm the paper’s claims. - GLM 5.2 costs $6.21 while Opus 4.8 cost us
- "I'm still writing the code. I'm just not doing it the same way I did." (1:21)🐧 Linus Torvalds gets angry when people say 99% of our code is written by AI, he told the audience at the Open Source Summit.
- Tokenmaxxers ngmi 😔I've warned about this many times. The brain is like a muscle. If you don't exercise it, then its strength decreases.
- I already love this product and have signed up for the preorder. Haven't had social media on my phone in years.The 80s Cell Phone Is Here In 1982, Commodore developed and marketed the world's best selling computer, the Commodore 64. Its success made Commodore one of the world's largest personal computer manufacturers. They have returned to their roots with a new “simple” phone. The
