Either way, really cool and impressive.

Matches my experience. Like 90% of the work is the spec.

Except instead of weeks researching its like a few hours talking with an agent.

interestingly my input is still pretty important

I am no longer:

- reading docs for hours and hours

- typing (barely at all)

- writing code

- manually doing tight debug loops

- using an IDE

to do this I had to give up reading or even controlling the code and focusing on behavior/design-level control (not superficial, still dictating overall technical architecture)

i have agents doing everything from writing the code, verifying the code, hardening, increasing test coverage, analyzing behavior, algorithmic perf improvements, managing/deploying to cloud resources, etc... (pretty much everything)

and I am accomplishing projects that would take months or years in a fraction of the time.

that's way more than 10x.

somehow, this is harder and more cognitively demanding than writing code

needle in a haystack is not good for this, yes it proves the model can attend to its context, but in its usual form, somewhat trivializes the query-key relationship.

something like long-form Q&A would be more ideal. Like reading a book and answering questions that require synthesizing information derived from either the whole thing or disparate portions of it. Like describing an entire character arc in a 1000 page novel with examples and evidential moments.

I wouldn't rely on it for large stuff like codex though. I haven't tried out deepseek/kimi, if we could run those locally it would be great.

orchestrator -> parallel subagents with investigation, authoring, verification, benchmarking subagents and integration / final verification handled by parent has improved my productivity too.

I feel like from here its agent swarms against a whole spec but haven't got there yet.

Still getting plenty of bugs in the more complex scenarios, but mostly (in some projects) i never have to look at the code and treat it like a black box

This grew out of a larger post where I try to explain diffusion models in less-dense terms, especially the parts that felt non-intuitive to me when first reading the papers. That post emphasizes that diffusion models incrementally “step” toward a solution rather than generating it all at once, and this interactive zooms in on that sampler-step idea specifically.

Would love feedback on:

- whether the interaction makes the sampler update easier to reason about

- what other diffusion concepts would be useful to turn into small interactives

Link: https://www.bryanthornbury.com/interactives/sampler-step-exp...

Comments URL: https://news.ycombinator.com/item?id=47200769

Points: 2

# Comments: 0

For many (including myself) who haven’t stretched those particular math muscles since diff eq class a decade or so ago, the paper is just an opaque wall of literal Greek.

In this post I describe my personal understanding of diffusion models in less-dense terms, focusing on intuitive understanding and personal mental models I use to understand diffusion.

Comments URL: https://news.ycombinator.com/item?id=47200240

Points: 2

# Comments: 1

Lots and lots of tests!

In another view, standard libraries do a pretty good job.