Claude Code lack of token issue. I tend to forget to put the models back in
Claude Code lack of token issue. I tend to forget to put the models back in, leave simple tasks to Fable, and waste them... Anthropic actually came up with a solution for this. ``A smart model takes care of the partitions, and chores are sent to multiple Haikus in parallel.'' I recommend it because you can set it up with one prompt and Claude will sort it out automatically. Details are below↓…
Grok 4.6 just locked in #1 on CursorBench for real-world coding.
Not only is it sitting at the top of the performance chart, it’s also on the efficiency frontier. Frontier-level coding results at a cost most models can’t touch. Claude Fable 5, Opus 5, GPT-5.6 Sol… all behind.
GLM 5.3 Max vs Qwen 3.8 Max vs Grok 4.6 vs Opus 5
GLM 5.3 Max is actually holding up really well here. My ranking for this run: Opus 5 > Qwen 3.8 Max > GLM 5.3 Max > Grok 4.6 Definitely competitive now. GLM is getting scary close.
Programé un nuevo juego de un solo prompt con Claude, pero esta vez lo hice mucho más desafiante
Le di una foto de mi living y le pedí que cree un juego en 3d en el que el protagonista es un bebé y su objetivo es tirar y comerse la mayor cantidad de cosas antes de que lo
You have reached the end of the archive
All of Claude Opus 5