Used chatGPT voice all night for my shift as a copilot last night. 

Realizing the power of its Memory function now. Quite useful. It remembers cases we have discussed before and also knows my work setting to understand capacity of treatments.

Physician always trying to learn, passionate about healthspan and precision medicine.

omarsaleem.xyz

how did you use it during your shift? recording and talking about cases between appointments / seeing the patients? what kind of advice were you mostly looking for?

(sorry about all the questions but very interested in your actual usage - former MD here, I don’t practice)

medicine

AI Case Test #2

Llama's responses are great. As an experienced clinician, the LLM added nothing new but I expect novice clinicians would gain a great deal by passing their patient cases through the LLM.

I am testing LLM/AI models on different medical cases I encounter.  In this case we use Llama 3.3 and further refine our System Prompt.

Venice.ai 's LLM responses are vastly improved when using the System Prompt feature.  I also opine that LLMs will provide better responses to better interviewers.

Link to the Substack post: https://open.substack.com/pub/largelanguagemedicine/p/large-language-medicine-2?r=2tr7dt&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

No worries! Great questions. I actually had this issue and it really helped using Voice instead of typing. And just working through thoughts and differentials. This was after talking to patients. 

Had an interesting patient with purpura and pulmonary findings so working through that with chatgpt was powerful. It’s extremely reluctant to give one diagnosis because it acts like a 3rd med student and overloads itself with information.

This is a great guide by @0x-omen.eth. As mentioned, having a system prompt is very powerful to steer the model in the right thought process from the start.

0x-Omen.eth

$Degen Maxi and bull-poster

Leveling up as a Solidity dev

Creating Phenomenon and Flex

Practicing physician every other week

building fiids.xyz, bondes.xyz and wyat.live

No worries! Great questions. I actually had this issue and it really helped using Voice instead of typing. And just working through thoughts and differentials. This was after talking to patients. 

Had an interesting patient with purpura and pulmonary findings so working through that with chatgpt was powerful. It’s extremely reluctant to give one diagnosis because it acts like a 3rd med student and overloads itself with information.

This is a great guide by @0x-omen.eth. As mentioned, having a system prompt is very powerful to steer the model in the right thought process from the start. https://warpcast.com/0x-omen.eth/0x7e0d8240