Ash Jogalekar
@ashjogalekar.bsky.social
I write about medicinal and computational chemistry and drug discovery with a sprinkling of history. Blog at medchemash.substack.com.
Once again we find out that AI algorithms are based on memorization of training set cases rather than any kind of understanding. This makes them brittle and unable to adapt to new cases (of which there are many). I think a hybrid approach would probably work best.
October 8, 2025 at 7:59 PM
Once again we find out that AI algorithms are based on memorization of training set cases rather than any kind of understanding. This makes them brittle and unable to adapt to new cases (of which there are many). I think a hybrid approach would probably work best.
In a nutshell: the authors perturb the binding site of known protein-ligand binding modes in a variety of ways, most of which should have abolished binding. But the AI algorithms (Boltz-1, Chai-1, AF3) still place the ligands in the exact same pose, ignoring clashes and forming spurious interactions
October 8, 2025 at 7:58 PM
In a nutshell: the authors perturb the binding site of known protein-ligand binding modes in a variety of ways, most of which should have abolished binding. But the AI algorithms (Boltz-1, Chai-1, AF3) still place the ligands in the exact same pose, ignoring clashes and forming spurious interactions
RFK Jr. for "advances in vaccine innovation." Hits too close to home though.
October 7, 2025 at 6:32 PM
RFK Jr. for "advances in vaccine innovation." Hits too close to home though.
Will read the paper, but does "folding-docking-affinity prediction" indicate a co-folding method? Because those are new.
September 24, 2025 at 9:37 PM
Will read the paper, but does "folding-docking-affinity prediction" indicate a co-folding method? Because those are new.
That was an unhinged, foul-mouthed performance even by Measles F. Kennedy Jr.’s standards.
September 4, 2025 at 9:27 PM
That was an unhinged, foul-mouthed performance even by Measles F. Kennedy Jr.’s standards.
Reposted by Ash Jogalekar
"Since I take solace in the belief that God looks after drunks, little children, and the USA, I still think maybe, somehow, out of chaos will come something good." —Graham Allison
September 4, 2025 at 6:10 PM
"Since I take solace in the belief that God looks after drunks, little children, and the USA, I still think maybe, somehow, out of chaos will come something good." —Graham Allison
Things math and facts are for losers. Winners simply use their imagination.
August 25, 2025 at 6:22 PM
Things math and facts are for losers. Winners simply use their imagination.
We gave our infant son one literally the other day because the doctor showed us data on a COVID summer surge. I personally know at least two people who just got it last week from travel. We are living in the shadow of an administration who would deny the sky is blue.
August 25, 2025 at 5:58 PM
We gave our infant son one literally the other day because the doctor showed us data on a COVID summer surge. I personally know at least two people who just got it last week from travel. We are living in the shadow of an administration who would deny the sky is blue.
Sheep who vote for a wolf because they think he will only eat other sheep.
August 25, 2025 at 5:57 PM
Sheep who vote for a wolf because they think he will only eat other sheep.
10/ The key message is that we can use the same tools that are used to do harm to fight that harm. If AI is used by bad actors to design WMDs, AI can also be used to defeat or anticipate that misuse.
August 25, 2025 at 5:27 PM
10/ The key message is that we can use the same tools that are used to do harm to fight that harm. If AI is used by bad actors to design WMDs, AI can also be used to defeat or anticipate that misuse.
9/ Ultimately this is a classic dual-use dilemma: these tools are hugely beneficial for doing good, but as Feynman once put it, the same key that opens the doors of heaven can open the doors of hell.
August 25, 2025 at 5:26 PM
9/ Ultimately this is a classic dual-use dilemma: these tools are hugely beneficial for doing good, but as Feynman once put it, the same key that opens the doors of heaven can open the doors of hell.
8/ The fix: Shift to living lists updated in real time, integrate AI into threat prediction, and partner with AI developers that can anticipate and not just react to emerging threats. Organizations like the OPCW should adopt a "function first" approach.
August 25, 2025 at 5:26 PM
8/ The fix: Shift to living lists updated in real time, integrate AI into threat prediction, and partner with AI developers that can anticipate and not just react to emerging threats. Organizations like the OPCW should adopt a "function first" approach.
7/ Policy problem: The Chemical Weapons Convention lists are static, structure-based, and slow. It took 27 months to list Novichok after its first known use. AI won’t give us that kind of lead time.
August 25, 2025 at 5:26 PM
7/ Policy problem: The Chemical Weapons Convention lists are static, structure-based, and slow. It took 27 months to list Novichok after its first known use. AI won’t give us that kind of lead time.