註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Tinker
@tinkerapi
I tink, therefore I am. Post-training API by @thinkymachines
加入 January 2026
1 正在關注    14.6K 粉絲
We highlighted how OpenResearch+Tinker make exploratory research easier, but equally important is auditing: testing dozens of competing published methods in an automated way with the compute cost forecast to within a dollar. We love to see our research grants support great work!
顯示更多
Using Tinker with an autoresearch loop is a really effective way to reproduce post-training papers at predictable costs Today there are dozens of self-distillation methods all claiming improvements over each other, and it’s hard to establish which claims hold up We gave agents a Tinker budget to reproduce self-distillation results across models and training setups. With just a few user prompts, they reproduced SDFT’s continual learning benefits across Qwen3-8B and Qwen3-30B-A3B over multiple seeds, and investigated SFT’s failure modes. Read more below:
顯示更多
0
0
144
19
轉發到社區