Viewing profile — entee

A lot of this post relies on the recent open ai result they call GDPval (link below). They note some limitations (lack of iteration in the tasks and others) which are key complaint…

I think what’s missing is what the software allows. It could be BMW/Merc etc are way more conservative on what the allow the system to do and when they force the driver to take ove…

Transcription factors often are partially disordered, just to name one. A bunch of others here: https://www.nature.com/articles/nrm3920

> It’s only marginally less useful to actual biology than full on X-ray structures anyway. I'm not sure what you're implying here. Are you saying both types of structures are usefu…

Such a database would be hugely helpful across chemistry. Right now it’s extremely expensive to access databases like Reaxys or Scifinder, and they’re not usually programmatically …

As a fellow perfectionist who has started a company, one thing that has helped me is realizing that most decisions are a lot more reversible than they appear. Even in the legal and…

There's a lot that can be learned with building-block based experiments. If you do a building block based experiment then train a model, then predict new compounds, the models do g…

This is true. Getting datasets with the necessary quality and scale for molecular ML is hard and uncommon. Experimental design is also a huge value add, especially given the enormo…

Not a chiphead, but saw this in the article that might be a reason ARM is better for this kind of thing: "The theory goes that arm64’s fixed instruction length and relatively simpl…

Most of the methane comes from cattle belching, so it's basically impossible to harvest at scale. The lagoons of manure also do, and that can be harvested though it's hard. https:/…

The catalyst is the part I'm most curious about. Carbon capture is a hard problem at scale. Once you have methanol, I'm not terribly surprised that you can convert it to other thin…

I'd agree if it works as advertised. Level 5 or very close to it is the key. No system has shown that, much less Tesla's. In the meantime, doing a live experiment with 3,000+ pound…

I drive a lot, thanks. If you can prove me level-5 or even very good level 4 autonomous driving, and that a computational driver makes radically fewer fatal mistakes than a human, …

I'm not sure what you're arguing in terms of acceptable risk. Biotech is incredibly regulated, specifically because the risks are so high, effectively there is very little acceptab…

It’s pretty clearly the current best way to do deep learning on molecules in chemistry. Transformers do really well in predicting reaction outcomes but GCNNs are still better when …

We already do all of this in drug discovery research before putting things into animals. We try computer modeling (very inaccurate but a good pre filter) then cell culture, and onl…

Even if the amyloid hypothesis is true (and most neuroscientists I know think it's not), this is a terrible decision. 1.) We don't know when to give the drug. Maybe giving it even …

That linked post is fundamentally wrong because it rests on an assumption that has essentially zero human evidence: amyloid causes Alzheimer’s. There have been several drugs that v…

Just got a postcard from my optometrist the other day saying it’s time for my annual prescription check. My eyes are no different, but my glasses are scratched, so I need to spend …

My biggest worry with this would be the low level of off target edits and the number of recombination events that yielded an unwelcome product. Looks like those were very low, but …

The first iPhone famously only had 2G cellular internet. At the time 3G phones were not ubiquitous but were readily available (had one as a mid priced Nokia flip phone), so I’ve al…

A couple other perhaps more useful quotes from the same article: “Despite Trump’s assertions, few close observers of Obama’s and Biden’s response to H1N1 consider it a “full scale …

That’s a pretty disingenuous link. The Bush administration did have a plan for Flu and was thinking about the issue. In 2015 (your article recounts stories of H1N1 in 2009) the Oba…

I can't upvote this enough. We HAD a plan, both Bush and Obama put together pandemic response plans. We had serious issues in logistics and deployment for sure. We had some screw-u…

Those who think the CDC has done way too much because the virus was overly-exaggerated are simply wrong. I have my quibbles with the CDC, especially early reactions and subsequent …