These two https://www.youtube.com/watch?v=oXBGZoBYaLY must be best dorm neighbours ever then.

That's fairly cool.

I probably couldn't listen to that on a regular, but I enjoyed it.

Thanks!

Do you use anything to orcheatrate multiple agent pitted against each other (coder, reviewer, tester, etc)?

Currently just manual. I'm not pushing the frontier here, just getting my feet wet.

While both Claude Code and Codex are capable harnesses, I definitely think there's a lot more to be gained from the harnesses. Quite a few of the times I needed to nudge the steering wheel it was things that a separate agent with the right prompt could have picked up on.

How would one create custom tools for it? opencode offers TS SDK for it, but with rust it will be something more heavyweight like gRPC bridge (similar to how terrafoem providers work).

> 5% would already be well within the margin of difference for separate identical clean installations of windows on the same hardware.

what is the source of this non-determinism?

Did you evaluate other projects, like openspec, before deciding on spec-kit?

Feels like it can be solved wirh even more AI: adverserial models reviewing and testing work performed by main model.

Actually I am curikus to try somwthing like that myself. Is there an existing orchestrating engine (or single agent) which can spawn multiple subagents and keep passing their feedback/output between each other until all of them agree that assignment overall is complete?

Ultra-optimized HW-specific engines is what Mojo lang seems to be targeting, but I rarely hear about it here.

> Mojo lang seems to be targeting, but I rarely hear about it here

Momentum over at Mojo lang seems very very slow.

According to their roadmap, they're still busy on Phase 1 ("High performance CPU + GPU coding"), and haven't touched Phase 2 ("Systems application programming") and Phase 3 ("Dynamic object-oriented programming").

So perhaps there isn't much to talk about?

They've got a lot of work yet to do to be a general purpose language, but for GPU programming they have already demonstrated that they can outperform CUDA on Nvidia GPUs.

That's pretty compelling.

1670 on Netflix was hilarious

I hadn’t come across this before. Looks really good, thanks for sharing

old sysadmin trick: create large file on a disk and in a dire situation when DB runs out of space delete it.

Genuine kubernetes scaling strategy: add a do-nothing container that runs with a lower priority than your real workloads, that requests half a machine’s worth of mcpu.

When you deploy a new container, and all your nodes are fully allocated, that low priority container will get evicted, and your container will immediately get scheduled in its place. Then k8s will try to find somewhere to put that half-machine container. If it finds somewhere it fits, it’ll schedule it. If not, it’ll trigger your cluster auto scale to add a new node where that task can run, making sure the next container you want to deploy has some readily available capacity to drop on to.

Basically the same sysadmin strategy, automated.

Or on Amazon elastic filesystems... create giant files just to ensure you're in the right performance class for the files you do need (that was the official way of doing it for a while!).

The classic Speed Up Loop

https://thedailywtf.com/articles/The-Speedup-Loop

Zero it first.

My layman question is why plastic cant be painted? Case temperatures are not that high and there are no plastic parts rubbbing.

This is answered in the first paragraph of the article. Painting requires re-calculating the weight, strength and aerodynamics. Paint does not weigh zero, it changes the flexibility of the plastic, and the texture which changes flow.

But the article didn't give any ballpark numbers, so the interesting bit is missing, and we still know basically nothing.

It can very well be like the snake oil which makes you feel better maybe for the three seconds after you bought it. Or those gold plated audio jacks which are 0.0001% improvement in quality.