Brian Pridgen, MD @HandEManAI

hand & microsurgeon. dad. building a future for patients, physicians, and agents. bringing top 1% healthcare to everyone. https://t.co/goyUm3km7l | https://t.co/eE2wzDX31t surgiscribe.co San Francisco, CA Joined November 2024

Tweets

180
Followers

108
Following

256
Likes

165

Brian Pridgen, MD @HandEManAI

43 minutes ago

@danshipper Did @mikeyk refer to Claude as “he” at 13:23? I can’t tell for certain from the audio, but I think so. I’m genuinely curious how people at Anthropic feel about Claude and whether he / it has a consciousness or any sort of awareness or personhood.

0 0 0 32 0

View Details

Brian Pridgen, MD @HandEManAI

2 days ago

@edkeonl Yikes. Use it now before it leaves the subscription plan!!

0 0 0 11 0

View Details

Brian Pridgen, MD @HandEManAI

2 days ago

And here it is in clinician mode.

0 0 0 5 0

View Details

Brian Pridgen, MD @HandEManAI

2 days ago

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 0 0 20 0

View Details

Brian Pridgen, MD @HandEManAI

2 days ago

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 0 0 42 0

View Details

Brian Pridgen, MD @HandEManAI

2 days ago

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.

0 0 0 16 0

View Details

Brian Pridgen, MD @HandEManAI

2 days ago

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 0 0 10 0

View Details

Brian Pridgen, MD @HandEManAI

2 days ago

@jxnlco Interactive HTML in React

0 0 0 20 0

View Details

Brian Pridgen, MD @HandEManAI

4 days ago

x.com/handemanai/sta…

Brian Pridgen, MD @HandEManAI

6 days ago

@sama 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

0 0 0 207 0

0 0 1 65 0

View Details

Brian Pridgen, MD @HandEManAI

4 days ago

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 0 1 335 0

View Details

Brian Pridgen, MD @HandEManAI

4 days ago

@Papa_Heme surgiscribe.co

0 0 0 25 0

View Details

Brian Pridgen, MD @HandEManAI

4 days ago

I’ve been building SurgiScribe to solve this (and the AI scribe issues mentioned in your replies). It started as a pain point with operative reports. But now it works for any arbitrary clinical note. It allows me to document at the speed of talking but with full control over the structure of the note. Let me know if you’d like to try it out.

1 0 0 311 1

View Details

Brian Pridgen, MD @HandEManAI

6 days ago

@weswinder I hit my 5 hour limit today for the first time in a month. So sad. 😞

1 0 1 359 0

View Details

Brian Pridgen, MD @HandEManAI

6 days ago

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.

0 0 0 207 0

View Details

Brian Pridgen, MD @HandEManAI

6 days ago

Looking forward to this being made available in your AI Edge Gallery macOS app. And related to the app, it would be GREAT if you had a feature where we could enter a prompt and have a response generated in 2+ panes where each pane is running a different model. Would make it much easier to compare capabilities between 2B, 4B, 12B for prototyping.