tmach32

Oh, good lord. Thank you. I'll beg the mods to have that fixed.

Interestingly, the Jev founder just posted on Twitter that they see themselves as more of a _data_ company.

I think one difference between OpenJev and Jev would be, then, is what it's trained on.

Jev is, on the surface, cheap enough for me not to seek self-hosted alternatives. On the other hand, I wish the free/open weight alternatives to Pangram were better.

I remember Bucky Fuller writing how seeing an airplane fly overhead used to be rare.

In my own childhood, seeing a satellite fly overhead used to be rare.

Now I see one every 2 minutes.

I used Superpowers for a few weeks. I ran into a couple issues:

* I wish I could turn it on selectively. Many of my requests do not require the "verification before completion" and TDD ceremony. For example, agents using stock Superpowers will go so far as to grep a file every time you ask to add something to them to verify that the edit really landed.

* While I like speccing out/designing a project before implementation (nothing new in that regard), I don't like how precisely superpowers plans out the implementation in the /writing-plans skill. It tells future agents exactly what files to edit. There are two big issues with this:

  * We need to manage context rot. If one LLM session is responsible for writing out the entire plan, we aren't solving context rot. Not only is the "smart window" of context exhausted by the time the agent is planning, eg, step 7 out of 15, but it's also dragging forward all the possibly bad ideas it had earlier. It would be better if steps were planned independently.

  * Implementation is an iterative process. You find things out as you go. Your assumptions turned out to be wrong, you realize APIs don't behave the way you thought you did, etc. This is why writing out a precise plan ahead of time is an issue – it's written without this iteration.

IMO, the strongest part of Superpowers is /subagent-driven-development. Yes, it's SUPER slow. For a laugh, you can ask it to make a change you know can be done in one line. It'll do it in one line, but it take literally an hour with all the verification. But that's sort of the point. It is _very_ deliberate. For each step, it reviews the step for both compliance and code quality, then has another agent implement the fixes, _and then it reviews the fixes again_. It does this for every step (not at the end of the project). While this might seem like overkill, it leads to code which complies with the spec far better.

Instead of writing a super detailed spec, I think I'd like /writing-plans to come up with appropriate "units" of work (sometimes called slices) and to brainstorm with the user regarding implementation, but to leave it looser than "edit this exact file in this exact way". That should leave a lot more leeway to implementation agents but still give the review agents something to check compliance against.

See also: JuiceFS, S3FS, and quite a few others.

We have done loads of research into using object storage wherever we can (given how cheap it is compared to SSDs), and so far it seems like making your application object store-aware is a far surer bet than abstracting S3 behind the file system. The behavior is just too different.

I'm more interested in applications that cleverly use object storage, e.g. AutoMQ, which is quite compatible with Kafka APIs but needs no HDDs.

This opinion is so quaint that it makes me smile.

For me, the #1 feature of the Advantage2 is ortho. Everything else is a distant second. I don't understand how anyone can use anything but ortho.

Yes, another layout would make your fingers travel even less, but ortho lets you reduce a lot of seeking/travel without learning anything new.

Why would anyone take this benchmark seriously? Cursor is obviously biased here. They can design it and its presentation however they want to tell the story they want to tell.

I think one thing people are missing about this article is that they are arguing that the harness can make a bigger difference than the model. They aren't merely hyping GLM 5.2.