I'm a junior at Northeastern studying CS + Math, really just trying to build something impactful that lends to the future of agents
- New Haven, CT
-
10:43
(UTC -05:00) - https://alex-lop.github.io/Alex_Lopez_Website/
- in/lopezalexan
Highlights
- Pro
Pinned Loading
-
Graphene
Graphene PublicTrying to make the collaboration w/ agents better so you have an idea of what's going on with your agent
Python
-
Sieve
Sieve PublicMost clinical trials don’t stall because the drug doesn’t work. They stall because they can’t find enough patients. Sieve shows which eligibility criteria are to blame, before you launch
Python
-
-
Nemisis
Nemisis PublicKills your worker after the money moves, replays the event, and proves whether an AI patch really survived the crash. Deterministic evidence, not model confidence.
Python
-
erdos-195-odd-difference
erdos-195-odd-difference PublicPartial progress on Erdős #195: a permutation of ℤ with no monotone 4-term AP of odd difference, formalized in Lean 4 (done with Claude)
Lean
-
erdos-197-bounded-lag
erdos-197-bounded-lag PublicPartial result on Erdős #197 (still open), verified in Lean 4: no two-set solution with both enumerations of eventual lag ratio below 2. Produced with Claude Opus 5.5.
Lean
If the problem persists, check the GitHub status page or contact support.