rishabhaiover

Those additional sentences are fairly non-trivial to construct, would you agree?

io_uring?

That's a great point. Linux has introduced io_uring, and I believe that gives us the native primitives to hide latency better?

But that's just one piece of the puzzle, I guess.

That's true but the capability to go back to an older iteration, reflect and find the correct solution (for odd numbers) is, in my book, a sign of undeniable intelligence.

I wholeheartedly agree. Glad to see his work on the front page.

Every week, I read an article on the consequences of reliable coding agents in SWE industry. All such discussions on HN leads to a fundamental suspicion of the empirical scaling laws of LLMs or the infinite greed and short-sightedness of the market in inflating a bubble. I'm tired.

I was reading a paper on dark silicon and how it broke the beautiful scaling laws of the past (Moore's law/Dennard Scaling). We hit a wall, innovated and at the moment, the hardware industry is thriving. To me, that means scaling the industry and riding that momentum wasn't wrong. In fact, it allowed us to be where we are today.

Why are we so against, in principle, to the current pre-training scaling laws? Perhaps, we'll require new innovations at some point, but the momentum allows us to reach to newer heights that we've never climbed before.

haha the NSFW toggle is crazy

A high-level language or a compiler wasn't automating end-to-end reasoning for a programming task.

I'm already seeing a degradation in experience in Gemini's response since they've started stuffing YouTube recommendations at the end of the response. Anthropic is right in not adding these subtle(or not) monetization incentives.

I found it a remarkable transition to not use Redis for caching from Sonnet 4.5 to Opus 4.6. I wonder why that is the case? Maybe I need to see the code to understand the use case of the cache in this context better.

is it anything like the OpenAI ad model but for tool choice haha

I'd be very interested to learn about output quality vs token utilization for both these approaches

For a second I assumed you meant 69 but then it hit me, i'm getting old.

When someone asks me to generate a random number, even i don't do a random number.

Claude Opus 4.6 says the same

slop is not a thing anymore, stop living in a fantasy world

Individuals believe they act freely, but they are constrained and directed by historical forces beyond their awareness - Leo Tolstoy

Between a challenging job market, increasing new frontiers of learning (AI, MLops, parallel hardware) and an average mind like mine, a tool that increases throughput is likely to be adopted by masses, whether you like it or not and quality is not a concern for most, passing and getting an A is (most of my professors actively encourage to use LLMs for reports/code generation/presentations)

pick any cs class

As a student, I constantly worry about this. But everyone in my class is producing output at a pace I can't compete with without AI assistance.

And then some alignment, prompting structure, and task decomposition.

I think I made a cursory and incorrect assumption. Given this is backed by Apple's Virtualization, it has POSIX compliance and forks/execs are allowed within the sandbox which can support agent parallelization within a sandbox I believe.

Looks like a great project at surface!

I've noticed claude forks parallel agents on an assigned task. How would they communicate in isolated sandboxes like these? Would it be cleaner and more effective for a harness to orchestrate swarms of agents in a single clean linux environment like OrbStack?

I think it would be useful to categorize the data on the basis of ailment fix/benefit rather than chemical targets for the general population

Thank you for sharing it, kind sir. Your explanation on b+trees (https://planetscale.com/blog/btrees-and-database-indexes) is probably the best one I've ever seen on the internet.

It's an absolute pleasure reading planetscale blogs. I'm curious about what tool is used to make these visualizations?

AI-generated content vs human-generated content is merging as such a fast pace that such a list doesn't seem like a scalable general solution

I think we're past the point where benchmarks hold real value. All models are above a certain threshold of intelligence but Gemini somehow borrows the worst of both worlds. It's neither good with long-horizon coding tasks nor does it offer a likable personality (like Claude which is much more beloved)

it's a dry scone