Joined November 2024
- Tweets 216
- Following 263
- Followers 122
- Likes 208
24 Photos and videos
Pinned Tweet
May 30
Thrilled to be one of the 4 Voice Hack Night finalists with Surgical Triage!
I built a voice-first AI workflow that handles emergency hand surgery transfer requests, patient details, images, and next steps in one conversation. As a hand & microsurgeon, I look forward to having this agent available one day!
Huge thanks to @OpenAIDevs and @cerebral_valley
Vote for Surgical Triage → cerebralvalley.ai/e/openai-v…
What’s one way voice AI could transform your clinical workflow?
May 30
🩺 Surgical Triage
A voice-first workflow for triage: transfer requests, patient details, images, and next steps in one place.
cerebralvalley.ai/e/openai-v…
1
3
10
1,532
Jun 12
Sign up for beta access to Luminos. It uses the latest ChatGPT model with "Sign in with ChatGPT" functionality, which is available with even free plans. Luminos is no cost to the user.
It uses:
1. latest ChatGPT model
2. agentic search over PubMed and other resources
3. a UI that ask questions to give the user the answer they're looking for
Jun 12
For medical information, general AI frontier models (Google, OpenAI, Anthropic) outperformed specialized @EvidenceOpen and @UpToDate as assessed by 12 US clinicians, randomized and blinded to which model and extensive testing/benchmarks. This was not anticipated. @NatureMedicine
nature.com/articles/s41591-0…
2
1
4
468
Jun 12
Here's a patient-facing answer from Luminos about stopping Ozempic.
The answer is grounded in citations from PubMed, structured as an interactive document with a quick answer, deep-dive sections, and exportable PDF.
luminoshealth.co/share/RXdSD…
45
Jun 12
Here's a physician-facing answer from Luminos: restarting anticoagulation after a GI bleed in the setting of afib.
The answer is grounded in citations from PubMed, structured as an interactive document with a quick answer, deep-dive sections, and exportable PDF.
luminoshealth.co/share/sTZLi…
1
39
Jun 9
As a practicing surgeon, I built Luminos, a medical research agent designed to improve the UI/UX of medical information retrieval.
On OpenAI's HealthBench Professional it scored 57.9 on low reasoning, just behind OpenAI's ChatGPT for Clinicians (59.0) on extra high reasoning.
1
70
Jun 9
Here is Luminos in patient mode. You ask in plain words, it gathers context, and then it answers with the evidence and citations you can check.
Join the beta waitlist. I'd love your feedback: luminoshealth.co
1
38
Jun 9
ChatGPT for Clinicians set the bar I measured against, and it is genuinely an excellent tool. The larger point is that OpenAI has created an environment where a practicing surgeon can build a harness that operates near the capability frontier and use it to explore the interface layer for medical intelligence. I believe that clinician-facing layer is where a lot of the remaining value lives, and I look forward to exploring it further.
1
21
Jun 9
Huge thanks to @OpenAI for the 10x Codex boost this past month and to @thekaransinghal and team for making HealthBench Professional available. I am deeply interested in putting excellent medical intelligence within everyone's reach, and I would love to connect with anyone building toward it.
24
Jun 8
With the last 10x boost, I achieved near parity with ChatGPT for Clinicians using my own clinical harness. But with low thinking.
I also did an audit of peer review medical publishing, which is only possible with a tokenmaxxing plan. Findings were interesting and are forthcoming.
And placed third in an OpenAI Hackathon.
All as a “non-technical” physician.
Would love another boost to push these further!
@thsottiaux
1
1
346
Jun 8
Jun 6
Huge thanks for the 10x Codex boost after the GPT-5.5 party invite. I tokenmaxxed hard (~1B tokens/day, peaked at 2.4B) on coding and non-coding tasks.
The result... My clinical harness Luminos (GPT-5.4 low-thinking) now nearly matches “ChatGPT for Clinicians” (GPT-5.4 high-thinking) on HealthBench Pro on a blind eval.
This was just one of several tokenmaxxing projects during the bounty. Full numbers and charts coming next week. Excited to share!
Here's the top line teaser graph.
1
76
Jun 3
Did something happen with Codex usage limits? I went from ~80% weekly usage a couple hours ago to 0%. I'm on a 20x plan with the 10x boost from the 5/5 event.
@jxnlco @thsottiaux
10
1
81
12,977
Jun 3
I've been trying to squeeze out every last token before I lose my 200x abundance, but I didn't think I was pushing it that hard! Good to know I'm not the only one.
Any chance we can get an extension on the 6/5 cutoff for the 10x boost?? 😂
1
4
1,131
Jun 2
Is there a bug in the latest Codex app release? I'm getting this 'gpt-image-2' error on numerous threads, none of which should have anything to do with images. This blocks the thread from progressing or doing anything else.
@thsottiaux @jxnlco
1
733
Brian Pridgen, MD retweeted
The future of voice starts with Chat.
Last week, we partnered with @OpenAI to bring builders together at OpenAI's SF HQ to showcase what's possible with the latest realtime voice models.
From AI companions and sales agents to translation and education tools, teams pushed the boundaries of voice-first experiences – with winners decided by a community vote.
Voice is becoming one of AI's most exciting frontiers.
What got built:
7
5
31
2,683