We're a small contractor bridging the cultures between AI and formal methods, motivated by threat models in which AI capabilities don't stop going up. Let's harden infrastructure, synthesize an SL5-grade cloud stack, etc. Step one is evals and RL envs.
Forall LLC
AI security via formal methods
- 6 followers
- United States of America
- https://for-all.dev
- quinn@for-all.dev
Popular repositories Loading
-
awesome-secure-program-synthesis
awesome-secure-program-synthesis Publicvibecoding, but correct and safe and secure and
-
-
formal-CuTe
formal-CuTe Publicstuff like this https://research.colfax-intl.com/categorical-foundations-for-cute-layouts/ in Lean
Lean 1
-
Repositories
Showing 10 of 17 repositories
- aisec-invariants-mlir Public
for-all-dev/aisec-invariants-mlir’s past year of commit activity - git-history-evals Public
harnessing all the naturally occurring proof engineering data as evals | PROTOTYPING we haven't invested in the finalization/comms yet
for-all-dev/git-history-evals’s past year of commit activity - pydanticai-inspectai-shim Public
Drop-in shim that converts pydantic-ai agent runs into inspect-ai .eval logs
for-all-dev/pydanticai-inspectai-shim’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…