sshah03

Looks like they decided to spend a lot of time/effort on visual, and motion/animation abilities with Hy4. I wonder if they have a reason for targeting that or if it was just a response to Opus and Astra gaining a lot of attention for those abilities (or from distilling Astra?).

What about its design stood out from the competitors, in your opinion? It sounds like you feel like the design was better, but the feature set was worse?

This was resolved for me. The e-mails were a red herring and not the actual reason, not sure what's going on there that triggered those.

What I keep wondering for these, is if there's a way to surface great projects that just haven't been marketing well, or at all. I'm not entirely sure what signals would allow for that, but it'd be interesting to test I think.

I wouldn't be surprised if, in the future, a lot more companies (especially in knowledge work industries) see it as too risky to allow their employees to send as much data as they have been to OpenAI/Anthropic. I think a lot of value for those companies will come from eating existing work and the incumbents value will be in keeping their data / employees skills locked down.

To add to this, I actually did look back through my e-mails and find an e-mail from GitHub from a year and half later confirming my access to Github For Education had expired as I did not re-verify ...

So somehow, something got triggered that sent people (at least myself) and e-mail if we had Github for Education at some point in the 2010s to re-verify within 30 days even if you weren't actively enrolled, while simultaneously suspending the account.

If anyone from Github or Microsoft reads this, please reply and let me know what can be done, as this definitely feels like an error on Github's part.

Built a tool that helps me at least get a better gist of complex changes: https://github.com/sshah03/perspica

It's not perfect, but it's helped so far.

The repo: https://github.com/sshah03/teach-me

I had built a tool called perspica (https://github.com/sshah03/perspica) for semantic PR diffing, and in it I built in the ability to get LLM generated explanations of the major changes in the PR, architecture changes, etc... Along with interactive examples, and quizzes to test if you understand the concepts behind it, to help keep up with AI code changes. You can see some of its sample generations on PRs of popular public repos here: https://sshah03.github.io/perspica/

I spent a lot of time iteratively running examples on a ton of projects and PRs and modifying the prompt to help generate diagrams and questions I felt were actually useful.

One of the key learnings for anyone doing anything similar, at least with the 5.5 family of models, is that when you run on a few cases, you might feel the need to get very specific on how to solve for common scenarios etc... And any time I tried this the results got worse. It seems to like well written general guidelines, and the models are so capable now that the rest gets handled pretty well. Similarly, trying to build in error detection into the initial prompt works much worse than an adversarial pass (even with the same model), but obviously this slows the whole thing down ... so I'm still trying to work out how to balance that.

I figured rather than force people to use my whole tool for that, I'd extract what I learned works well into a claude code plugin/skill that can do the explanation/quiz part of what perspica does and store it as artifacts on the users Claude Code account, which is what this skill and repo is.

I'd love to hear where the explanations miss or the diagrams get something wrong so I can keep working on improving it for everyone. I considered not posting it, since it was just a Claude skill, but I'm interested in using peoples experiences with it to improve it, since getting something that works well for the diagrams generically has proven to be a bit tougher than I expected.

I considered doing this with an open source app I have that let's you get a visual summary on a PR + get quizzed on it, but ultimately decided it's better to keep it an optional thing for people that want to understand AI PRs rather than force it as a gate, the volume is slowly becoming too high for even that. I agree with the sentiment behind this though as I felt this was needed as well.

Looks interesting! I was trying to figure out a good way to add some of the benefits of this right into the actual gh review flow, but haven't quite figured out the smoothest way to do it yet.

Thanks! Added enough that you should be able to give it a try. I'll work on improving Scala support over the next few days.

If you're interested in using this, but your language of choice is presently unsupported, just leave a reply here with the language and I'll prioritize adding it. Also any other requests, or suggestions that would make this genuinely useful to you as well.

Windows should also be supported now, though let me know if you run into issues with it there as it isn't as well tested.