As a vibe coder in biotech, I've been thinking a lot about LLM safety filters and jailbreaks β prompting techniques that bypass them.
I found these topics to be an instructive lens into LLM internals, so wanted to share my notes in this short thread & blog post π§΅
Thrilled to share our recent work in @emboreports@EMBOPress that uncovered actin waves in lymphocytes, which rescue antigen receptor loss during immune responseππ. Super thankful to @India_Alliance@ANRFIndia@Infosys@MOE-STARSπππ
https://t.co/utPcYHhbdg
Thread below:
Introducing reversible molecular simulation: differentiable simulation but with constant memory.
Useful for training classical and machine learning force fields to match experimental data. Feedback very welcome!
https://t.co/YOm8Bi0VI5
(1/8)
Protpardelle π came out in @PNASNews last week! highlights of new results:
- backbone-only model compares with RFdiffusion
- flow-based likelihoods predict designability
- better filtering on AFDB improves quality and diversity
- measure scaffolding and repacking performance
When I came to US for graduate study, in 1986, the Harvard International Office made Ed and Jane my host parents. βMy father likes math,β their son told me. βMe too,β I said. Years later, I learned that Ed invented chaos theory. https://t.co/n0WAnCqcId
Our third year hosting this program. It has been incredibly rewarding for all of us in the team to interact with amazingly talented PhD students. Looking forward to another summer of fun science!
Hey @tim_cook if you see a spike in M2 Ultra and M3 Max sales in Q4, please look at your Apple Machine Learning Research team.
They did the magic: MLX πͺ
https://t.co/l8tACp9TP6