In fact, synthesis of pure Haskell powered by SAT/SMT (e.g. Hoogle, Djinn, and MagicHaskeller) was already of some utility prior to the advent of LLMs. Furthermore, pure functions are also easy to test given that type signatures can be used for property-based test generation.

I think once all these components (LLMs, SAT/SMT, and lightweight formal methods) get combined, some interesting ways to build new software with a human-in-the-loop might emerge, yielding higher quality artifacts and/or enhancing productivity.

[1] https://www.anthropic.com/research/small-samples-poison

[2] https://arxiv.org/abs/2510.07192

You should consider publishing a patient case report somewhere, as I believe there are lots of valuable conclusions to be extracted from your work.

Given that you carry the HLA-B*27:05 allele, you might have been blessed by being predisposed to a better response. But probably you want to keep an eye on future autoimmunity issues. Talking from experience...

Comments URL: https://news.ycombinator.com/item?id=47550016

Points: 18

# Comments: 9

That's a good observation, but I think it's an incomplete picture. Another important constraint is often regulatory inertia and historical baggage.

The UK pioneered small classical and adaptive trials using Bayesian methods, and there were some promising results. A lot of modern Bayesian methodology was, in fact, developed at the MRC BSU Cambridge with this goal in mind. For example, the probabilistic programming language BUGS (1989).

Given that most drugs fail, the industry is highly incentivized to use Bayesian methods to fail faster. These models allow for more rapid dose-finding and the ability to distinguish promising leads using interim data, which is vital given the massive cost of any trial, especially late-stage failures.

But for Bayesian methods to make a dent, they'd need to be applied to a large number of trials, and change doesn't happen overnight. Lots of big pharma players, e.g. GSK, are becoming interested in moving to Bayesian methods in order to leverage prior information and work better within small-data regimes.

In a CLI, oath lets you calculate a TOTP.

But it's maybe a bit more insecure if you use the same machine.

They might also be great combined with early-stage detection via ctDNA.

But in late-stage patients, the effectiveness is limited because the host immune system is compromised.

Several landmark mRNA cancer vaccine trials by BioNTech and others have pointed in this direction.

In vivo reprogramming of T cells might be the next frontier. In fact, the BioNTech founders are moving to a new venture, but it's unclear what their thesis is.

Controlling Hungary is enough to veto some support for Ukraine.

Personally, I am a heavy user of Firejail and bwrap. We need defense in depth. If someone in the supply chain gets compromised, damage should be limited. It's easy to patch the security model of Linux with userspaces, and even easier with eBPF, but the community is somehow stuck.

Comments URL: https://news.ycombinator.com/item?id=47498222

Points: 114

# Comments: 18

There are lots of old ideas from evolutionary search worth revisiting given that LLMs can make smarter proposals.

Non-parametric optimization is not a new idea. I guess the hype is partly because people hope it will be less brute force now.

Comments URL: https://news.ycombinator.com/item?id=47481997

Points: 3

# Comments: 0