Viewing profile — namin
namin
HN member- Joined
- Thu, Aug 09, 2007, 9:50 PM UTC
- HN karma
- 743
- Public activity
- 122 items
- HN profile
- View on Hacker News ↗
About namin
No profile information was provided.
Recent public activity
- story
-
story
Show HN: LemmaScript, a verification toolchain for TypeScript via Dafny
I created LemmaScript to compile TypeScript to a verification backend (Dafny or Lean) and prove properties on the systematically derived model. I'll keep developing this, but I hav…
- story
-
comment
Comment #47300540
Thanks, we will provide case studies. Already today, lemmafit doesn't need familiarity with Dafny. It is used under the hood, so you just use Claude Code normally and lemmafit adds…
-
comment
Comment #47299951
Since around Opus 4.5, systems like Claude Code are very good at Dafny proofs. They don’t get everything right in one shot but can iterate with verifier feedback. Some proofs take …
-
comment
Comment #47299586
Hey HN! We've been experimenting with Dafny formal verification in web apps. We've been using AI to write verified state machines, proving undo/redo preserves invariants, verifying…
- story
- comment
- story
-
comment
Comment #46908125
Ha. At least you can check the theorem statements and see that the proofs verify :)
- story
- story
- story
- story
- story
- story
-
comment
Comment #45801028
Harvard SEAS | https://metareflection.seas.harvard.edu and https://namin.seas.harvard.edu | Postdoctoral Fellow | Greater Boston Area | ONSITE I am looking for a postdoctoral fello…
- story
-
story
Show HN: Live software archaeology of FOL (theory of reasoning)
I want to share this live playground for FOL, an old system from the late 70s. It has many precursor ideas about reasoning at the meta-level, including the now common proof by refl…
- story
- story
-
comment
Comment #40853192
Harvard SEAS, ONSITE (Boston area, MA, US) I have one opening in a new project around AI for precision medicine. One thrust is about combining biomedical knowledge graphs and large…
- story
-
comment
Comment #40640106
Awesome, thank you! I'll check it out.
-
comment
Comment #40635533
This seems cool! Is there a way to try it locally with an open LLM? If you provide a way to set the OpenAI server URL and other parameters, that would be enough. Is the API_URL ser…