Jaehyuk Lim

Karma: 37

Inner-aligning AI and trying to ask better questions.

Jailbreaking ChatGPT and Claude using Web API Context Injection

Jaehyuk LimOct 21, 2024, 9:34 PM

4 points

0 comments3 min readLW link

HDBSCAN is Surprisingly Effective at Finding Interpretable Clusters of the SAE Decoder Matrix

Jaehyuk Lim, Kanishk Tantia and Sinem

Oct 11, 2024, 11:06 PM

8 points

2 comments10 min readLW link

Biasing VLM Response with Visual Stimuli

Jaehyuk LimOct 3, 2024, 6:04 PM

5 points

0 comments8 min readLW link

[Question] SAE sparse feature graph using only residual layers

Jaehyuk LimMay 23, 2024, 1:32 PM

0 points

3 comments1 min readLW link

Identifying Micro-friction in the Context of the Anterior Mid-Cingulate Cortex (aMCC)

Jaehyuk LimMar 29, 2024, 10:11 PM

3 points

0 comments3 min readLW link

Language Models Don’t Learn the Physical Manifestation of Language

Bruce W. Lee and Jaehyuk Lim

Feb 22, 2024, 6:52 PM

39 points

23 comments1 min readLW link

(arxiv.org)