GrepMed retweeted
Medicare gives hospitals an inflation update every year. Doctors don't get one.
Then everyone wonders why practices sell.
Then everyone wonders why practices sell.
9
34
200
12,380
GrepMed retweeted
A breed bred to fight viciously with minimum provocation and maximum bite strength ends up killing more humans than all other breeds put together, but the respectable explanation is "bad training."
124
300
3,498
174,525
GPU Jesus @JensenHuang is the š but someone please tell him to stop repeating this nonsense- AI has not taken over radiology. There has been little real penetration into the field and imaging demand has increase has had zero to do with AI.
5
1
14
2,688
Was inspired by this post to try a quick GPT6 Astra test for medical education- I always had trouble remembering the various eponymous shoulder physical examination maneuvers...
Okay, this is genuinely impressive.
I asked GPT-6 Astra to help me understand my own ankle pain. It gave me a full interactive 3D atlas ā bones, ligaments, tendons, real motion axes, sliders for plantarflexion and inversion, and a live readout of what each ligament is doing.
One session.
6
38
316
30,082
A year ago for fun I vibe-coded a Gorilla vs 100 men game... it took several days of painful iteration (4o). Today one-shot prompted this (gpt6 high) š¤Æ
stockdips.ai/GorillaGauntleā¦
stockdips.ai/GorillaGauntleā¦
2
0
4
3,258
The @grok (4.6 high) version I simultaneously made for comparison (also pretty damn good but not as polished)... like Astra, it took one prompt to get 99% then 3-4 cosmetic prompts to fix some basic physics fixes.
stockdips.ai/GorillaGauntleā¦
stockdips.ai/GorillaGauntleā¦
1
0
1
259
GrepMed retweeted
Only if education could be this interactive ā¤ļøāš„
I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it.
A 3D human anatomy application built with @threejs using GPT 5.6 Sol.
It all started with a single design image that I created then used it to generate every 3D organ image, one by one.
Next, I converted each of those images into 3D models using @tripoai (and no, they didn't sponsor this š).
After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models.
Codex built the first version beautifully, but there was one big problem.
Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps.
After a few iterations, Codex optimized each model down to roughly 2ā5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand.
Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that.
The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step.
It genuinely felt like building something that could make learning anatomy much more engaging.
The inspiration came from @DilumSanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day."
And I did it :D
Live: anatomy-livid.vercel.app
Code: github.com/thebuggeddev/aā¦
I've had a looong wish to build something genuinely useful through vibe coding, and I finally did it.
A 3D human anatomy application built with @threejs using GPT 5.6 Sol.
It all started with a single design image that I created then used it to generate every 3D organ image, one by one.
Next, I converted each of those images into 3D models using @tripoai (and no, they didn't sponsor this š).
After that, I opened Codex, wrote a master prompt based on the design, and gave it the prompt, the design image, and all the 3D models.
Codex built the first version beautifully, but there was one big problem.
Every single 3D model was nearly 120-150 MB. That obviously wasn't practical for the web and was giving a performance of 16fps.
After a few iterations, Codex optimized each model down to roughly 2ā5.5 MB while preserving the visual quality, reducing the total asset size from ~900 MB to just 28.6 MB. And each model loads on demand.
Along the way, Codex also generated those anatomical illustrations showing where each organ sits in the human body, and even created the interactive hotspot markers that explain different parts of every organ. It handled all of that.
The process wasn't exactly one shot, but it also wasn't difficult. You just have to do it step by step.
It genuinely felt like building something that could make learning anatomy much more engaging.
The inspiration came from @DilumSanjaya's 3D animal plant cell project. I remember seeing it and thinking, "I want to build something like this one day."
And I did it :D
Live: anatomy-livid.vercel.app
Code: github.com/thebuggeddev/aā¦
619
1,562
12,055
2,129,653
GrepMed retweeted
Hey @DrOz,
When you started practicing medicine in 1993, the RVU reimbursement rate was $31.60. @CMSgov is proposing that in 2027, it is $33.40.
Adjusted for inflation (+132%),
thatās a 54% cutā¦
No wonder you quit practicing medicine. The financials donāt make sense.
Can you tell @CMSGovā¦oh, wait a minuteā¦
š¤š¤Øš
When you started practicing medicine in 1993, the RVU reimbursement rate was $31.60. @CMSgov is proposing that in 2027, it is $33.40.
Adjusted for inflation (+132%),
thatās a 54% cutā¦
No wonder you quit practicing medicine. The financials donāt make sense.
Can you tell @CMSGovā¦oh, wait a minuteā¦
š¤š¤Øš
We're proposing one of the biggest Medicare updates in yearsāstrengthening primary care, expanding accountable care, and modernizing physician payments. The goal is simple: help clinicians spend less time on paperwork, more time with patients, and deliver better outcomes.
21
114
641
78,290
GrepMed retweeted
This is definitely the weekend to know where your closest reimplant centers are located. Not all Level 1 trauma centers, particularly pediatric standalones have this capability.
A starting point but NOT inclusive of all capable centers can be found here: account.assh.org/s/hand-trauma-ā¦
A starting point but NOT inclusive of all capable centers can be found here: account.assh.org/s/hand-trauma-ā¦
0
1
4
711
GrepMed retweeted
Neat paper:
Women lose weight:
- Life drastically changes
- Men start approaching, a third partner off ASAP
Men lose weight:
- Their weight decreases
Women lose weight:
- Life drastically changes
- Men start approaching, a third partner off ASAP
Men lose weight:
- Their weight decreases
GLP1s for weight loss impact lives beyond health. My new paper shows single womenās marriage/cohabitation rates rise 29pp, employment among nonemployed women rises 27 percentage points after 1.5+ years.
Link to paper below:
172
593
14,612
2,475,805
GrepMed retweeted
Medicine discovers the bitter lesson: frontier LLMs (here GPT 5.2, Opus 4.6, Gemini 3.1) outperform specialized "clinical AI" (e.g. OpenEvidence) in a blind test.
Even funnier that hospital IT are more likely to approve the *specialized* versions despite them being worse.
Even funnier that hospital IT are more likely to approve the *specialized* versions despite them being worse.
For medical information, general AI frontier models (Google, OpenAI, Anthropic) outperformed specialized @openevidence and @UpToDate as assessed by 12 US clinicians, randomized and blinded to which model and extensive testing/benchmarks. This was not anticipated. //t.co/KCH1ADfQWz
29
160
1,144
188,230
