Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Making Claude a Chemist

anthropic.com

Post reply on HN
Print view View original

91–97 of 97 posts

Re: Making Claude a Chemist

#91

Post by ElFitz »

gilleain wrote: post #79
Obscurity4340 wrote: post #74

Earlier quoted context omitted.

Why is ferrocene ungraphable or in this context unable to be modelled in that way?

I meant metallocenes in general: https://en.wikipedia.org/wiki/Metallocene A metal atom sandwiched between two Cp rings. You _can_ model this as 5 single bonds between each atom of a ring (so 10 total C-M bonds), or you have to have some kind of 'edge' (bond) between the ring as a whole and the metal. The more general issue is that a graph model of a chemical assumes a 'bond' is between exactly two atoms. Three-cente…

From what I found, current state of the art on modelling "reaction space" with graphs that is to use "hypergraphs" where edges can lead to more than one node[^0].

But I am just someone who got curious; not even an amateur ^^’

[0]: https://pubs.acs.org/doi/10.1021/acs.jcim.5c00265

Re: Making Claude a Chemist

#94

Post by LearnYouALisp »

moffkalast wrote: post #19
jgilias wrote: post #9

Earlier quoted context omitted.

> Even if you get the right molecule, it might be the wrong way around or just clump up into a useless mess. Sounds a lot like vibe coding lol

At least vibe coding can only explode in your face metaphorically.

"Show HN: Klapotke.io: Novel Synthesis of Energetic Compounds by Generative Methods"

Re: Making Claude a Chemist

#95

Post by chaostheory »

OutOfHere wrote: post #86
chaostheory wrote: post #82

Earlier quoted context omitted.

sure, but how else would you better guarantee safety? How else can we avoid annoying guardrails? Besides, it's not like you can't have different agents with skills collaborating

Safety is a lie. It's always possible to divide a task into subtasks, to use abstractions, and the LLM will allow each of these individually. For example, If you want it to write malware, break that down into a hundred high level steps, then implement each one individually, then stitch them together. A dumber but uncensored agentic LLM will even do this for you to control the censored smarter LLM.

If safety is a lie, then the arguement for massive and overbearing regulation and controls gets a massive boost

Re: Making Claude a Chemist

#96

Post by solumunus »

MiracleRabbit wrote: post #23
andai wrote: post #21

If they succeed here, won't they have to gate access to this feature, too? For the same reasons as, "if I so much as mention mitochondria, it downgrades me to Opus." Step 1. Make it so Claude can do anything — the whole point of AGI Step 2. Wait, if the user can do Anything, that would be Very Bad! Step 3. Err on the safe side with blanket bans of entire fields The latter actually seems to me a sensible reaction to e…

I just wait until a Opensource model inhaled all the chemistry books and papers. Lol. They are following closely and the best offer 80-90% of the performance and come with a very small fraction of the costs.

No they don’t.

Re: Making Claude a Chemist

#97

Post by voidmain »

andai wrote: post #21

If they succeed here, won't they have to gate access to this feature, too? For the same reasons as, "if I so much as mention mitochondria, it downgrades me to Opus." Step 1. Make it so Claude can do anything — the whole point of AGI Step 2. Wait, if the user can do Anything, that would be Very Bad! Step 3. Err on the safe side with blanket bans of entire fields The latter actually seems to me a sensible reaction to e…

Providing access to the public is presumably just a temporary stopgap for these companies until they have robot armies to replace their customers and employees.
Post reply on HN