But there are a lot of analogies to computation in bio as a physical, atomic forces-driven, massively parallel computer, so it's possible there will be something related to electronics and computers that falls out. For example, there's also applications directly related to other fields including DNA storage of data and neuron-based computation.

It's hard to quantify the impact of new foundational tools like this at launch. Most of the time it falls flat, but even the successes are difficult. For example, CRISPR has led to interesting experiments and treatments on the way, but the effect does feel muted compared to the initial predictions. But there are many other related techniques that can be pulled out of this original research (e.g. dCas9 which lets you operate without cutting).

Similar story with cellular reprogramming.

Eventually one of these things will surface that will be GPU/transistor type innovations.

I'm missing the advantage of using git for this. (Not criticism, genuinely want to know).

> Audio: We simplified audio processing even further. We removed the audio encoder entirely and projected the raw audio signal into the same dimensional space as text tokens.

There was considerable backlash and discussion on twitter/reddit, as well as some support.

Comments URL: https://news.ycombinator.com/item?id=48265512

Points: 2

# Comments: 1

They really captured the urge to build things in tech, and the problems that come with it. HACF, Silicon Valley, and The Soul of a New Machine are a trifecta.

On the other hand, I'm hopeful that this will help me get out of bed just a bit faster.

Comments URL: https://news.ycombinator.com/item?id=47932552

Points: 1

# Comments: 1

Where it gets interesting is that if I were to naively construct this accumulator in a non-computational, infinitesimal manner, I would probably start using the idea that the infinitesimal accumulation is related to the instantaneous slope and using that somehow with the previous accumulation. But this is going the opposite direction of derivatives that the fundamental theorem uses.

I understand there are a few other types of integrals that slice things different ways that might be more intuitive. I vaguely recall some (non fundamental theorem) proof that made Riemann integrals click for a while.

I feel similar about the trace of a matrix being equal to the sum of eigenvalues.

Probably this means I should sit with it more until it is obvious, but I also kind of like this feeling.

He was also nice and approachable in person, which to be honest I didn't expect from the utilitarian no chit chat rules on SO.

> More effort control: Opus 4.7 introduces a new xhigh (“extra high”) effort level between high and max, giving users finer control over the tradeoff between reasoning and latency on hard problems. In Claude Code, we’ve raised the default effort level to xhigh for all plans. When testing Opus 4.7 for coding and agentic use cases, we recommend starting with high or xhigh effort.

The new /ultrareview command looks like something I've been trying to invoke myself with looping, happy that it's free to test out.

> The new /ultrareview slash command produces a dedicated review session that reads through changes and flags bugs and design issues that a careful reviewer would catch. We’re giving Pro and Max Claude Code users three free ultrareviews to try it out.

Comments URL: https://news.ycombinator.com/item?id=47763024

Points: 2

# Comments: 0