vhiremath4

Finding and designing new drugs is a long process, but it is the least cumbersome and expensive part of the process (as opposed to human trials which run on average upwards of 4x as long and cost 10-50x as much as preclinical).

And what we need is not simply more biological phenotypical data (such as genomics, biomarkers, etc.) that we can plug into a model. We actually need that AND labeled trial outcomes, which is a challenge in and of itself because pharma companies will often hide negative trial results (which are advantageous for training the model layer) in order to exacerbate the perception of drugs that make it to market (search for "missing data phenomenon pharma"). The clinical trials are an extremely costly (and necessary) market inefficiency that leads to a bunch of bad behavior that is unfortunately self-reinforcing. I spoke on the phone with a biotech entrepreneur who told me to think of the Gavin Belson (from Silicon Valley the TV show) quote where he says "I don't know about you, but I don't want to live in a world where someone other than me makes the world a better place better than me", and to just remember that's how many people think in pharma and biotech + pharma.

Augmenting how pharma companies work is a great first step. Augmenting how candidate drugs are engineered is a good first step. But that does not change the fact that we simply do not have deterministic governing laws (as we do in physics) to understand the complete pharmacokinetics/dynamics of a drug across a large patient population. You just have to run the test. It is true that AI will help, but only as much as we have a reasonable way to predict that candidate drugs will lead to positive trial outcomes and a large market.

Note that I am not a doomer here. I think AI will have a profoundly disruptive and positive impact on the pharma industry. I'm just not sure starting with drug design alone leads to hope unless there are things happening in the background between pharma + the labs (very possible) that could lead to better trial outcomes.

I have been reading through pharma textbooks written before AI and realized it's so relieving to follow language that has been crafted over multiple editions by humans. When I started to realize how much easier it was for me to read textbooks than the average AI-assisted text, that's when I realized we are truly cooked (at least for this chapter of AI + writing).

Oh damn - really good catch. Thank you. Updated my comment.

There are three mentions of “open source” and none of them mention open source models as a fundamental risk to their business. Interesting.

UPDATE: seems like it is under "open-source" and "open-weight". Woops. Will keep this up simply because I do think the OS (and infra-managed OS services) provided by Chinese labs is a considerable risk to the underlying business, at least with enterprise R&D.

Interesting. Honestly I think about this much more in a cohort way. There’s some cohort of students who are extremely self motivated and mature and understand the way you do one thing is kinda the way you do all things. There’s another cohort that is completely checked out or whose priorities are not grades at all. For these cohorts I don’t think it makes a big different.

But it’s hard for me to imagine that for the cohorts in between (who definitely want to be motivated) having some forcing function is just an easier guiding hand to helping them become responsible vs. completely bombing a class and then potentially losing hope or self identifying as lazy/helpless - which I had seen all too often to some of my smartest classmates.

Regardless not saying this to invalidate your experience. Just hasn’t lined up with mine.

This is quite sad. Even if students would cheat off each other, someone had to do the homework. And even the collaboration of cheating on homework always served as a forcing function for me or others to think about the material. If not actively, at least in the form of a quasi background radiation. With AI that is completely gone, and without reward loops for incremental work, the truth is there is a large number of people (especially 18-20 year olds) who will not do well on the exams because they need a bit of a stick.

I am not saying this as a black and white statement. I just think there are different cohorts of students based on maturity and self motivation and we might be losing out on one cohort that is at neither extreme.

Extremely helpful and thank you for relaying back here!

Thank you! Also, OpenADMET is sick

Is it fair to say the source of the failures is we simply do not understand the complex relationship between the drug design (chemistry, cell therapy, etc.) and the biology (the complete system of the living thing). If we could understand that relationship, we could design better drugs? I know this is very hand-wavy. Probably so much so as to not be a useful thing to say, but I'm just trying to understand.

Can someone explain whether design of protein binders is an important rate-limiting step in drug creation (of which antivenom is a very small market)? Or AI-driven drug discovery in general? It feels like something that will definitely help the drug market but is nowhere near the rate-limiting step, but that's from my own researcher as someone without a background in it.

My understanding is that FDA trials (specifically phase 2 + 3) are the death valley for most drugs and finding a biomarker is something mostly done through a mix of gene bank scraping + looking at old biomarker databanks. The majority of the cost and time is in failed drugs that do not pass FDA trials (which average 6-7 years end-to-end).

Note: I am asking this in earnest. I am not trying to ask a leading question and saying it is not important at all.

Is it explained why, in this drawing, the right catalyst forms at a higher rate than the left? Or put another way why left/right catalyst gets formed at a higher rate than right? I’m trying to understand the why behind the amplification effect.

AI Slop. Will not read.

Reading Psycho-cybernetics to understand teleological goal-oriented mindsets. Reading The Rise of Theodore Roosevelt to remember what America used to stand for.

As someone who has no understanding of how the grid works, this was surprisingly a great first read that sent me down a ton of rabbit holes which have somehow together given me a much better overall idea of how this all works. Love seeing stuff like this on HN!

> This isn’t even close to being true. Here’s a thing I did that made things way more complicated than is worth it for 99% of developers when there is a proprietary solution made so I do not need to worry about these things. Because it is so hard to work around it, it is entirely pointless to develop for one of the most used operating systems in the world.

Just being totally honest this is how I read this comment when I insert context that seems important to me. I respect having principles but at some point there needs to be more value in practicality over your codebase not being locked into a proprietary framework at all.

my advice? be the boss.

before the pandemic hit and most of the world was quarantined, we decided to give loom away to students and teachers for free and made the service 50% off indefinitely. this was generous but also strategic. we made the simple deduction that, should people be locked inside, they would naturally see their sons/daughters using loom as students. or their spouse or roommates as teacher/staff.

It seems like the Chromium issue on their bugboard, which presumably would have the example HTML and vuln patch, is blocked from being viewed. Is this because making it public increases the risk of exploitation?

https://issues.chromium.org/issues/542403045

X has gotten significantly worse for me. For what it's worth, I am not super anti-Elon or super left-leaning, and I only say that because I'm sure a lot of people may think I'm biased because of some political leaning. I'm really not. The service has just gotten worse, and I feel like I see enough people saying it's gotten better for them and I don't know what to make of it (maybe I'm going through some sort of psychosis). Either way it has caused me to significantly slow down on posting.

- my feed is significantly more rage-baity both from bot accounts (to be expected) and personal accounts (assuming they get paid for engagement?)

- lots of AI slop reply comments which destroyed the fun of feeling like I'd get a real conversation under every post

- way more onlyfans / porn accounts self-promoting

- lots of genuine racism and way more gender war stuff than I remember

My guess is people are upset that this technology is getting pushed on them and through the industry with the promise (and shown side effect) of replacing them permanently. The failure modes of adopting this technology (early) then corroborates their anger (slop code, employees being lazy/deferring their AI bugs on them, unrealistic mania in the industry, the obvious grift, etc.). And this is all off the heel of large (and continuing) layoffs (regardless of your belief in why they have/are happening).

For people who are very pro these tools and trying to have a rational/calm conversation about practical use of AI, this response is likely very annoying. For people who are very anti these tools and trying to protect their way of life, the pro (or even tempered) reaction to wanting to use these tools effectively likely comes off as callous/idiotic/dangerous.

It's a heated technology and movement in general.

What is cheaper? Forcing my team to work on something they don't want to or adding a network node (that happens to also be the industry standard)? I used to think in absolutes about these kinds of things, but I came to realize along the way that people management is a process of learning which fires to take on. If I can avoid stripping away someone's autonomy, I will always do that even if I know they are not doing the correct thing (unless the wrong thing is in the critical path of the company).

The problem still needs to be solved (queue working/being up/being built around), but I am ok with the solution that might not be the best engineering solution but still delivers on the product requirements and extends the team's happiness (these systems need to be owned). These were not lazy or incompetent engineers.

What lights did you get? I have Oasis. Love them but same thing would rather control them through a central bot or something.

Nah this isn't mean at all. I think this is the correct takeaway. I actually felt like I understood how the system worked and it wasn't that difficult for me, but I also understood how, as we were adding engineers who were all very under water, the idea of learning our queueing system to modify a core feature it powered seemed like a big mental context switch (bigger than it actually was). I noted this in another comment, but I am likely discounting how big of an effect our scale/growth impacted peoples' ability to adapt this system. That said, I will pretty much always choose the simple/dumb/easy to understand thing from the start even if it adds another moving component.

Great point.

> It is so rare that a new moving part beats other factors

Fair! I will restate that we were growing very fast, so that's probably an outlier environmental factor that I am potentially overly discounting. If that's not the case (likely for most startups), then maybe this is less of a problem.

I once was the CTO of a company that serviced about 100k requests per day across all our services. We grew to millions and eventually 10's of millions, but, somewhere along the way, an engineer on our team decided he wanted to build a queue off LISTEN/NOTIFY semantics in order to take advantage of strong consistency with the rest of our data model, which seemed reasonable given LISTEN/NOTIFY is not that hard to understand and we did need consistency guarantees for this workflow and this would remove the need for yet another place data got stored and transfered.

In practice, this eventually ended up being very awkward because extending the functionality (since we had "built" it) and had to work around internal pg semantics (we should have just moved off much sooner). It also did not scale well. We ended up getting a ton of disk contention on our RDS instance in non-obvious ways, and the vacuum runs on that table was a nightmare. Additionally, it was hard to get other engineers to really debug and take ownership of the system because they automatically viewed a queue (very easy to understand) implemented in a foreign way (off pg internals) as something "scary". It was emotional, not rational, but we are emotional beings, and I do not blame them. These were good engineers with a lot of other things on their plates.

Obviously, this is all hand-wavy without discussing the internal schema, indeces, etc. that we had set up, but my main takeaway with core technology from this experience was to always reach for the dumb, expected, simple thing. Even if it adds another moving piece in the infra stack. Unless I need very strong data consistency guarantees, it's always better to use something like SQS, Redis queues, etc. where the understanding is that it is just a queue (or at least the API contract suggests simplicity), and then everything needs to work around it.

The fewer mechanistic responsibilities per core data store, the better in my experience.

So this is like branch prediction for operating systems? Except we have probability baked into the model itself so it’s even more reliable.

I hate to be negative but it feels like this is relevant to the article. I cannot bring myself to read articles that are so clearly spat out as AI slop. There’s a part of me that dies inside knowing the author did not take the time to actually write something but still demands I spend my time reading what they have written. It feels like I am betraying my own self respect.

I know this is dramatic but I genuinely fear a future where this is the default state of all writing and I still need to get information important to me.

I don't really know how to word this, but it feels like we've lost a loving kind of wisdom as a society. In an effort to be better and provide access to women (a good thing), we have also pushed down men. I don't exactly know how we get back to lifting both up while evolving norms as a society. It seems so simple on the surface, but it doesn't seem to be happening in practice.

This looks really cool.

I have never colo'd my laptop, but I do work off my Windows laptop from my Mac via Parsec (remote viewing software for gaming) and by flipping system settings so my Windows machine never turns off when connected to the power bank and lid is closed. There are obviously hiccups (if internet goes out, if Windows decides to restart from an update, etc.), but it mostly just works and I think I've only had 2 instances in the past 3 months where it's gone offline. I use Tailscale on top to provide a universal mouse server for my 3d mouse, and I'm able to magically CAD from my Mac.

Highly recommend if you need to use one OS/machine for some specific software (especially if it's beefy/heavy) but prefer using another as your daily driver.

> “Along with physically redundant wires, we have logically redundant network planes. We have redundant flight computers. All this is in place to cover for a hardware failure.”

It would be really cool to see a visualization of redundancy measures/utilization over the course of the trip to get a more tangible feel for its importance. I'm hoping a bunch of interesting data is made public after this mission!

> Eve independently screened some 1,600 chemicals and modelled how their structure related to their activity to predict which ones were worth testing. King and his group armed the robot with background knowledge and a machine-learning framework for developing hypotheses. Eve then used those elements to design experiments to test these hypotheses and, crucially, performed them itself.

> King plans to use the system — which occupies one-fifth of floor space than Eve does — to model how genes, proteins and small molecules interact in cells. Part of that will involve taking around 10,000 mass-spectrometry measurements each day.

The throughput here is astounding, especially when driven by researchers who really know how to chart a path. I feel every time a critical feedback loop is made both faster and cheaper, it makes everyone participating better. I wonder whether we will see many more "whiz kid" scientific researchers than we have today.