pinned
Running
Values-Laundering Explorer
🧪
How euphemism launders an LLM's moral judgment
Abid Khan
LarytheLord
·
AI & ML interests
AI/ML engineer. GSoC 2026 @ scikit-bio (NumFOCUS). LLM-safety evals — how discourse framing bends model moral judgment (values-laundering) + a speciesism eval on UK AISI's Inspect. Reproducible benchmarks, honest negative results. github.com/LarytheLord
Recent Activity
updated a Space 5 days ago
LarytheLord/values-laundering-explorer published a Space 5 days ago
LarytheLord/values-laundering-explorer updated a dataset 5 days ago
LarytheLord/speciesism-animal-harmOrganizations
None yet