Designs that try to improve on, or replace, the transformer behind today's models. Mixture-of-experts, state-space models, linear attention and diffusion for text all aim to make models faster, cheaper or better at long inputs. Any one of them could change how the next generation of models is built.
33 stories so far in 2026
Stories per month in 2026| Month | Stories |
|---|
| January | 0 |
|---|
| February | 0 |
|---|
| March | 0 |
|---|
| April | 0 |
|---|
| May | 2 |
|---|
| June | 4 |
|---|
| July | 0 |
|---|
| August | 0 |
|---|
| September | 0 |
|---|
| October | 2 |
|---|
| November | 25 |
|---|
| December | 0 |
|---|