Tom Stanis

Founder & CEO of @StoryHealthAI

Previously Co-Founder and Head of Software @verilylifesci
Former Principle Engineer @Google

[Tom Stanis @tomstanis]

@jhuber It is the "reveries".

[Tom Stanis @tomstanis]

@rauchg Can confirm.

[Tom Stanis @tomstanis]

@dvasishtha I’ve heard that the barrier isn’t med map (it actually helps with this), but billing liability.

[Tom Stanis @tomstanis]

@cwhogg i kind of feel sorry for these guys

[Tom Stanis @tomstanis]

fun https://t.co/4jLwukkxm5

[Tom Stanis @tomstanis]

@dp_oneill Clearly we need to cut all this innovation out and get back to good old care denying as the differentiator.

[Tom Stanis @tomstanis]

https://t.co/1dX4yTZPH5

[Tom Stanis @tomstanis]

@dvasishtha There are non nostril pillows as well

[Tom Stanis @tomstanis]

@dp_oneill @cwhogg @StuartBlitz Diagnosis codes is my guess.

[Tom Stanis @tomstanis]

@StuartBlitz We can achieve both good access AND better relationships if we are clever.

[Tom Stanis @tomstanis]

This is going to help so many patients.

[Mark Cuban @mcuban]

If you take Entresto, we now have the generic and it starts at $33.75 !

It's probably lower than your deductible or Coinsurance. So check it out with your doctor !

[The Humanoid Hub @TheHumanoidHub]

Pollen Robotics, a Hugging Face subsidiary, has open-sourced Amazing Hand, a 3D-printable, four-finger robotic hand with eight degrees of freedom (DoF).

Weighing 400g and costing less than $250 - it is designed for Reachy2’s wrist but adaptable to other robots.

[Tom Stanis @tomstanis]

@nikillinit We did this in early days of Google. It was called Prophet. You could also short objectives.

[Tom Stanis @tomstanis]

@cwhogg bolt, replit, lovable are the hot ones... not sure the best.

[Tom Stanis @tomstanis]

@chrissyfarr Then they would be RSUs

[Tom Stanis @tomstanis]

@StuartBlitz What if I redline the methods of destruction?

[Tom Stanis @tomstanis]

That's a good validation of the problem.

Having the LLM write the code and call tools seems reasonable as that is how a human would do it... but I'm not sure I trust the LLM to write the correct code for general prompts.

Another approach I've considered is to break up the record into documents, have the LLM classify the documents, and build a knowledge graph. This is another way of solving the context limit problem. You can think of this as another version of the chain of thought pattern.

[Tom Stanis @tomstanis]

@JoshCMandel This is super cool. Josh, do you have any evals that you have built or thought about around this? I'm curious about your comment that "LLMs need tools to deal with this data". Would be great to see an eval to see where the tools can boost performance on tasks.