rahul
@0interestrates
CEO @JuliusAI | DeepFinance bench (first long horizon finance benchmark):
3.5K Following 69.1K Followers
Inkling 2 Small pushes the cost-performance pareto frontier for OSS models on DeepFinance bench
On long horizon finance workflows, Inkling 2 Small scores higher than GLM 5.3 for 50% of the cost, and nearly the same score as Qwen 3.8 max for 11% of the cost
Show more
claude fable 5.1 vs muse wonder 1.0
in @juliusai
we need a name for this kind of signaling ritual
un-introducing notebooks in @juliusai
are we just supposed to forget what they did to windsurf?
anthropic cto has an mba. narrative violation
warm intros are low agency. you can just reach out
we're launching sites in @juliusai today
when you ask AI tools to make you slides, most (including julius) will generate a nice looking html file.
which looks cool but isn't very extensible
today we're fixing that
guy selling post trained oss models: if you don’t own your models you don’t own anything
guy selling harness on top of models: if you rely on one model you are cooked
guy selling tokens: instead of manually prompting your models just put them in a loop where they prompt themselves
Show more
it’s incredible what swyx has built with aie in just three years
