— Arslan Nadeem (@arslannadeem04) March 2, 2026
Smaller models seem to be more complex. The encoding, reasoning, and decoding functions are more entangled, spread across the entire stack. I never found a single area of duplication that generalised across tasks, although clearly it was possible to boost one ‘talent’ at the expense of another. But as models get larger, the functional anatomy becomes more separated. The bigger models have more ‘space’ to develop generalised ‘thinking’ circuits, which may be why my method worked so dramatically on a 72B model. There’s a critical mass of parameters below which the ‘reasoning cortex’ hasn’t fully differentiated from the rest of the brain.
。业内人士推荐在電腦瀏覽器中掃碼登入 WhatsApp，免安裝即可收發訊息作为进阶阅读
having a pane be a terminal window was enormous, as opposed to relying on my terminal emulator to provide this functionality (and
Why the FT?See why over a million readers pay to read the Financial Times.
Blog: https://unipat.ai/blog/UniScientist