it's crazy that when i tell an agent to "run XYZ", i basically expect it to read 20 files every time just to figure out what the hell XYZ is. it sounds like engram will be big for model welfare
Alex Wettig
@_awettig
composer-ing @cursor_ai
- it's nice to see research bets pay off :)Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we’re doubling the included usage of the model.
- v happy with this! you can now use *much* more composer and still have all the credit left for opus and codexWe've raised limits for Auto and Composer 1.5 for all individual plans. Individual plans now have 3x usage of Composer 1.5 versus Composer 1. For a limited time (through February 16), we're increasing that to 6x.
- RL works?Composer 1.5 is now available. We’ve found it to strike a strong balance between intelligence and speed.
