Hacker Newsnew | past | comments | ask | show | jobs | submit | rohitpaulk's commentslogin

Wild how this beats 2.5 Pro in every single benchmark. Don't think this was true for Haiku 4.5 vs Sonnet 3.5.

Sonnet 3.5 might have been better than opus 3. That's my recollection anyhow

For those who haven't seen the actual issue that links to, I'd take a closer look. Pretty insane: https://github.com/actions/runner/issues/3792#issuecomment-3...


Yeah, calling the authors of this code losers and monkeys is being kind. There is zero excuse for ever writing code like this, the incompetence is staggering.


Always felt dependency updates are a perfect fit for AI agents:

(a) they’re broadly similar across companies,

(b) they aren’t time-sensitive, so the agent can take hours without anyone noticing, and

(c) customers are already accustomed to using bots here, just bad ones


One would imagine they are broadly similar; but that's off the assumption that codebases are similar as well.

Migrations between versions can have big variance largely as a function of the parent codebase and not the dependency change. A simple example of this would be a supported node version bump. It's common to lose support for older node runtimes with new dependency versions, but migrating the parent codebase may require large custom efforts like changing module systems.


I noticed this with Harvey / Legal.


Where do I buy one?



Love to know as well!


Link added above :)


- Contribute to OSS - Do CodeCrafters


Great content! Sidenote for the Fly team: on mobile, the “sidenote” cards appear in the wrong order - they appear before the content instead of after.


Yeah, we need to tweak them; they were designed for a wider browser window than a lot of people use. If they're not rendered as actual sidenotes, I think we should make them footnotes or popups.


The sidenotes also come first when reading with a screen reader, and there's no indication that they're sidenotes.

On the other hand, nice job with the alt text on the packet diagram. Maybe it sucks that the diagram itself can't be accessible, but I think you did the right thing in this case.


This has been a peeve of mine for awhile; we're going to "demote" them to pop-up footnotes when there isn't enough screen width to make them sidenotes. (In either case, you're better off than when they're in the main flow of the text).

Thanks!


Not exactly what you described, but https://labs.iximiuz.com/ is similar


thanks! I'll check it out


interessting, thanks!


Still involves friction. A more "seamless" way for Apple to do this would've been to license GPT-4's weights from OpenAI and run it on Apple Intelligence servers.


but that restricts it to just openai then.

I want to use perplexity from siri too!


This is a great idea. We’ve used Storybook & Chromatic in the past to cook up something similar for our front-end apps. There was quite a bit of setup work involved though.

How does integrating this into a web app work? Do you hook into an existing test suite? Record sessions on staging?


This is all automated. It's a github app that tracks changes as they come in, analyzes and simulates them and creates simulations that can be accessed via the CodeYam website, integrated into a CI workflow, or, hopefully soon, leveraged in developer workflows.

In this way there's no set up or maintenance required (or very minimal). It updates simulations as changes are made so everything is always up-to-date.

It automatically generates a number of scenarios (data that is fed into the simulation), but you can define new scenarios through the website as well (or describe a scenario for the AI to generate).


Definitely curious about how this works - signed up!


Awesome, we'll reach out soon!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: