brendanashworth
Joined 12 years ago
Karma
324
Submissions
65
Member since
Dec 7
Recent submissions
Comment · 6 months ago
Comment · 6 months ago
Out of the box, Opus/GPT-5.4 uses checks like `tsc --noEmit` or `python -m py_compile ...`, so compile checks on a Swift/Objective-C app probably get you pretty far. Also just setting up a Dockerfile maybe with swift:5.10-focal would give the agent the right tools to verify its own work.
Sandboxing isn't about having the perfect devex environment, most dev sandboxes (looking at codex cloud) don't actually have full verification available. Sometimes Github actions CICD is all you can get!
Comment · 8 months ago
Is there a reason people don't use SHAP [1] to interpret language models more often? The in-context attribution of outputs seems very similar.
Comment · 9 months ago
If choosing a Bayesian approach in a clinical trial can reduce the number of recruited subjects, I would imagine the pharma industry is strongly incentivized to adopt it.
Comment · 11 months ago
Would a wearable model like this gain in predictive power by adding FHIR/EHR inputs? CoMET [1] has great AUC even without daily/lifestyle metrics like steps, awakenings at night, or vo2max estimates (which are present in say apple health). It would be interesting to know how much you would gain from having a holistic model that sees both inputs.
[1] https://news.ycombinator.com/item?id=48028790