Independent R&D

Making computation fast on real chips.

AI models · GPU code · small devices · scientific simulation. Measured on hardware I own, with numbers you can verify.

Scope

Research tracks

All tracks →

My R&D asks one question: how does computation really run on real chips? I work on it through AI inference, GPU programming, small devices and scientific computing.

Latest result

Where does each lock hold?

Three ways of locking a language model compared on one Mac: safety training, a system-prompt instruction, and an outside filter.

Safety training wrongly stopped 2 of 100 harmless questions. Adding Llama Guard raised that to 21 of 100. A plain-text secret leaked in 45% of tricks on Llama; a simple code check cut leaks to 7.5%. Five runs each, 980 answers, on one Mac.

Caveats:two small models and one filter on one Mac; 40 questions in Set A and 12 in Set B, so differences of a few points are noise; one reader judged the answers and knew which setup produced them; a bigger model can behave very differently.

Field notes

Latest notebook

All entries →

Contact

Say hello

karthikjohnbabu@gmail.comGitHubLinkedIn