Tom Sanford, MD

Urologist, AI research

[Tom Sanford, MD @T_Sanf]

@EvanThomas84 @EvanThompsonMD, rad onc lecturing on abandoning PCa pts? That's rich. Do you fulgurate rad-ravaged bladders at 3AM? Accusing someone of malpractice without knowledge of their practice patterns is dishonest. Lets cut the BS: What is your % revenue from CaP IMRT/SBRT?

[Tom Sanford, MD @T_Sanf]

@jm_alexia For some use cases very tiny networks are amazing!

[Tom Sanford, MD @T_Sanf]

@rasbt Hoping to see ‘Grok 2.5 from scratch’!

[Tom Johnson @tomjohndesign]

This is how I feel about vibe coding.

Any project I try that has any kind of complication has this immediate burst of progress. Things are amazing and it feels like a superpower. Then... as I add more complexity, things crash to a halt.

The only projects that I think I can create are ones that fall in this "vibe zone". Prototypes, UIs, products—anything that's simple and has low complexity fits right in that zone. Proof of concepts, interactions, stuff like that. The tools are able to make things that fit in that slot.

But.

Everything falls to pieces as that complexity curve increases. And the problem is that any good product design process has increasing complexity. A basic prototype turns into a good prototype as soon as it has layered interactions, transitions, good affordances, hover states, 1000 tiny little details that make something feel correct and real.

The benefit of vibe coding is supposed to be that you move fast and you can whip things out—letting AI do all the work for you. The problem is it loses steam as soon as the necessary complexity is added. It keeps redoing itself, rewriting code, affecting things that are unrelated and then causing other issues.

But if you add that complexity, every vibe coding session quickly turns into a whack-a-mole bug-bashing session.

I'm not sure the solution to this. With traditional prototyping the solution is to duplicate, add more complexity, create more frames/scenes, tweak, fork, etc.

However with vibe coding, one little prompt can destroy literally everything. There's a stage where I end up walking on prompt eggshells-- trying not to give it too much or too little context so that it doesn't go rogue and break everything.

There's only a few exceptions to this. @cursor and @framer.

I can make great progress with Cursor, give it narrow context, and I have to approve the edits that it makes. This feels like a correct workflow. The problem is, I can't see the thing that it's making because it's an IDE, not a visual environment. Yes, I can create local builds and refresh my browser and all that kind of stuff. But the visual aspect is totally lost from the coding experience. It's a developer tool.

Framer gets this right because it only allows narrow updates within a single component on the page. Yes, it's limiting because it can only do a single thing at once, but at least it's not trying to create the entire page from scratch and manage it all through a prompt interface.

These seem like the right approach.

@Cursor: Allow the AI to edit anything but allow the user to approve those edits and see them in context.

@Framer: Allow the AI to only narrowly edit a single file or component to keep the complexity down to a minimum and reduce catastrophic edits.

I'm optimistic that tools like @Figma, @Lovable, @Bolt, and @V0 can make cool prototypes, but I just keep running into walls when it comes to doing anything more than just a basic interaction prototype. They need to do less IMO.

Hopeful that those tools add more controls that are in the same line as Cursor and Framer. I'll also add that this is similar to how we do it with @Basedash chart generation as well. But we're not a vibe tool in the normal sense so the parallels are a little bit harder to draw.

[Tom Sanford, MD @T_Sanf]

@Maryysakran No. Go watch lost and pretend you don’t know what happens at the end. I expect a full report on the smoke monster tomorrow, double spaced please.

[Akshay 🚀 @akshay_pachaar]

ML researchers just built a new ensemble technique.

It even outperforms XGBoost, CatBoost, and LightGBM.

Here's a complete breakdown (explained visually):

[Tom Sanford, MD @T_Sanf]

@Maryysakran Next time: more lube.

[Deedy @deedydas]

https://t.co/DPH5wBte2D

[Gabriele Berton @gabriberton]

I can't stress enough how useful this trick has been for me in all these years

It reduces GPU memory by N equal the number of losses, at literally no cost (same speed, exactly same results down to the last decimal digit)

For example ... [1/2]

[Tom Sanford, MD @T_Sanf]

@rdthorsett @cremieuxrecueil I notice you did not list the rate of the risks. Modern TP prostate biopsies have a mortality rate that is very close to 0 and serious complications are rare ( <1% clavien class 3/4). Prostate cancer remains the 2nd leading cause of cancer deaths in men, so risk vs benefit.

[Tom Sanford, MD @T_Sanf]

@krassenstein @grok One point worth noting is that between 2012 and 2018 the USPTF, the leading body for prevention guidelines, gave PSA screening a grade D recommendation, meaning it shouldn’t be done. Fortunately, that recommendation was reversed, but PSA testing remains controversial.

[Tom Sanford, MD @T_Sanf]

@EricLDaugh As a general rule (there are always exceptions), no - metastatic prostate cancer does not develop without a long lead time elevated PSA trend. This diagnosis brings attention to limitations in current guideline recommendations to limit PSA screening in men over 75.

[Tom Sanford, MD @T_Sanf]

@aidenybai Yes, the purpose of .DS_Storr is to ensure everyone who copies and pasts a file from a Mac to a Linux or windows environment experiences #pain.

[Tom Sanford, MD @T_Sanf]

@elonmusk @neuralink That’s cool. But first, can we have an EMR that takes less than forever to load when logging in?

[Tom Sanford, MD @T_Sanf]

https://t.co/EDVrdIVHuz

[Andrej Karpathy @karpathy]

There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.

[Tom Sanford, MD @T_Sanf]

@pmarca AI is certainly going to help patients and make doctors better. Some people (in my experience, most people) still find the human interaction component of medicine meaningful. And it may be a while before people feel comfortable undergoing a procedure by an autonomous AI robot.

[Tom Sanford, MD @T_Sanf]

So happy to see Honolulu install more bike lanes! Making cycling safer is a great way to encourage active transportation and make the city healthier.