531–540 of 748 posts
Earlier quoted context omitted.
Linters and tests help of course, but they cannot "fix" the problem since tests cannot prove the absence of bugs.
agree, and I think we'll see more use of formal methods with LLMs for this reason
It funny to see the community here expects the human body to be treated like a deterministic function: for input X expect output Y - and that transfers to diagnosis - people expect to receive the same diagnosis from different specialists for the same issue. Given human body complexity, the diagnosis is a compound output of the experience, knowledge gained throughout the career and diagnosis methods/equipment, the tit…
> It funny to see the community here expects the human body to be treated like a deterministic function In a community largely made of people whose job it is to produce such functions, I'd say it's to be expected
There's no shortage of tech people convinced they deeply understand law, medicine, philosophy, etc. despite never having read much on the topics.
https://karankurani.github.io/OpenCareLoop/
It has helped me personally solve longer chronic problems in my family that doctors just dont have the time to go into indepth due to their (understandable) lack of time.
Its in alpha and AI hallucinates. Use with care. Feedback welcome.
An AI agent for personalized healthcare is inevitable. The cases such as the one posted are all solvable with time. AI has hallucinated and continues to hallucinate but the value we get in the space of coding can be extended to other domains.
Earlier quoted context omitted.
The problem is how do you know whether the answer is just the most persuasive or actually the most accurate one? It's hard to figure this out without domain knowledge.
Take the output to a Radiologist and verify the veracity of the statements.
Earlier quoted context omitted.
I dunno, I could see it working. I do something similar with reviewing code: I have one agent write the code and another reviews it, then they go back and forth for a bit improving the code. Seems to yield better results than one agent alone. Seems like a similar principle.
The difference is that in the code situation, you can run unit tests on the code, compile it, etc. Unless your LLMs are ordering diagnostics and reviewing the results, there is no further information that the LLMs have on the situation. Having a second LLM review the first is counterproductive, if the 2nd LLM is better, why not use it directly? If not, then what prevents it from sending the first on some incorrect ta…
Earlier quoted context omitted.
Have you ever let the LLMs “discuss” with each other to see if that would give better answers? You might end up with the answer from the most persuasive LLM, but you might also end up with better results. Wonder if there is a paper out there on this.
The problem with trying to write a paper is the results depend on RNG.
Can any LLM give you the rough pixel coordinates of an item it identifies in an image? I found that while Claude, GPT etc could describe an image, there was no way to link the description back to specific pixels in the image itself. Not even to a bounding box or segment.
Earlier quoted context omitted.
I have multiple LLM subscriptions at any given time, plus an array of local models. When I ask a question outside of my domain of expertise I like to ask all of the LLMs I have access to. I also create separate sessions and ask the same question multiple ways. It’s revealing to see how many different and contradictory answers I get, most of which are presented confidently. The last time I ran a medical question throu…
In my day job we tried creating a credit assessor tool using LLM as the credit assessor. It did great, generated a report on the assessed business that was incredibly detailed and plausible. Then I started running tests and getting into the details, and found that if you ran the same report on the same data, it generated completely different, still very plausible, results. I could run the same source data through the…
Earlier quoted context omitted.
What happened to VERIFYING an answer? Does nobody do that anymore? When I ask an LLM, I trace the sources, and see if they make sense. More often than not the sources don't actually say anything about the topic in particular... > It’s also scary how easily you can lead each LLM to the answer you have in mind. Exactly. Which is why "treat an LLM like a human expert who can answer your question" doesn't work. It's more…
> When I ask an LLM, I trace the sources, and see if they make sense. Professional tip: you can cut out the LLM middleman here and save a lot of time and money.
I'm a radiologist but can't really weigh in without seeing the full 3D MRI dataset. Regarding this point: > They performed shockwave therapy on my shoulder even though a recent clinical practice guideline says clinicians should not use or recommend shockwave therapy for rotator-cuff tendinopathy without calcification; I was told during ultrasound that there was no calcification. Ultrasound isn't a great way to assess…
Radiologist who does read shoulder MRI would like to add that over half the annotations are wrong, glaring mistakes in anatomy and cardinal direction which begs the question of how is it making these findings without knowing what it’s looking at (here’s a hint, it’s hallucinated based on reports it sees).