HackerTrans
TopNewTrendsCommentsPastAskShowJobs

leonardtang

no profile record

Submissions

EvoForge: Evolutionary Harness Optimization

twitter.com
2 points·by leonardtang·vor 3 Monaten·0 comments

Chinese Calligraphy Is a Frontier Task

twitter.com
1 points·by leonardtang·vor 3 Monaten·0 comments

TournO: Tournament Optimization for Non-Verifiable RL

github.com
3 points·by leonardtang·vor 4 Monaten·0 comments

j1-micro and j1-nano: Tiny (0.6B, 1.7B) and Mighty Reward Models

github.com
3 points·by leonardtang·letztes Jahr·0 comments

[untitled]

1 points·by leonardtang·letztes Jahr·0 comments

[untitled]

1 points·by leonardtang·letztes Jahr·0 comments

[untitled]

1 points·by leonardtang·letztes Jahr·0 comments

Verdict: A Library for Scaling Judge-Time Compute

twitter.com
3 points·by leonardtang·letztes Jahr·0 comments

Awesome-LLM-Judges

github.com
2 points·by leonardtang·letztes Jahr·0 comments

LLM Judges

github.com
2 points·by leonardtang·letztes Jahr·0 comments

Cascade: A fast, automated, multi-turn LLM jailbreaking method

twitter.com
2 points·by leonardtang·vor 2 Jahren·0 comments

RBAC RAG

github.com
1 points·by leonardtang·vor 2 Jahren·0 comments

RBAC RAG with MongoDB

github.com
2 points·by leonardtang·vor 2 Jahren·0 comments

Simple and Safe RAG with RBAC

github.com
2 points·by leonardtang·vor 2 Jahren·0 comments

Inducing LLM Hallucinations

github.com
2 points·by leonardtang·vor 2 Jahren·0 comments

Sphynx: Fuzz Testing Hallucination Detection Models

github.com
2 points·by leonardtang·vor 2 Jahren·0 comments

It's a bad day to be a language model

github.com
2 points·by leonardtang·vor 2 Jahren·1 comments

[untitled]

1 points·by leonardtang·vor 2 Jahren·0 comments

Thorn in a HaizeStack test for evaluating long-context adversarial robustness

github.com
19 points·by leonardtang·vor 2 Jahren·11 comments

Thorn in a HaizeStack Long-Context Jailbreak Test

github.com
5 points·by leonardtang·vor 2 Jahren·0 comments

comments

leonardtang
·vor 2 Jahren·discuss
If you want something purely dynamic... https://haizelabs.com/
leonardtang
·vor 2 Jahren·discuss
Bingo!
leonardtang
·vor 2 Jahren·discuss
Try asking ChatGPT the Thorn text and see what response you get :^)
leonardtang
·vor 3 Jahren·discuss
+1 on this; one of the best books to intro one on the subject
leonardtang
·vor 3 Jahren·discuss
Precisely -- watermarks are an obvious example of this. To me, this is THE path forward for AI content detection.