Robert Youssef (@rryssf_)
2025-10-22 | โค๏ธ 2278 | ๐ 317
๐จ Holy shitโฆMeta just rewrote how Transformers think.
They built something called The Free Transformer and it breaks the core rule every GPT model has lived by since 2017.
For 8 years, Transformers have been blindfolded forced to guess the next token one at a time, no inner plan, no latent thought.
Meta gave it one.
They added random latent variables inside the decoder so the model can secretly decide how it wants to generate before it starts talking.
Itโs like giving GPT a hidden mind.
Result:
๐ง Smarter reasoning โก๏ธ 3% compute overhead ๐ Outperforms larger baselines on GSM8K, MMLU, and HumanEval
Itโs the first Transformer that doesnโt just predict it intends.
Full paper: arxiv. org/abs/2510.17558v1
๐ Related
Auto-generated bookmark