HNHacker News
TopNewBestAskShowJobs

orbis-tertius

43 karma · joined November 3, 2026

submissionscomments
orbis-tertius··on Show HN: Cosh – An open-source AI agent orchestrator
Very nice, and congrats on launch! It would be helpful if you could add to the README a summary of the key differences with other TUI orchestrators.
orbis-tertius··on I hate everything I vibe-coded. Here they are
I understand the feeling, and definitely share it sometimes. Feeling like we're losing expertise and ownership of our work sucks!

Maybe programming is just not an intellectually satisfying vocation anymore; but whichever format your ideas will take in the future, please don't stop having them and working on them! That would be such a waste

orbis-tertius··on Claude Fable 5.2 and Mythos 5.2
ctrl+f pelican
orbis-tertius··on I hate everything I vibe-coded. Here they are
I actually think many of these ideas are great, and they are technically correct and skillfully executed. So what's wrong with them? Is it the generic AI-slop taste? Or that there's no need for them? Are they bad, or are they useless (or both)?

What do all those failure modes have in common?

orbis-tertius··on On Being an Engineer in 2026
Yeah agree with this, these seem like genuine moats for now (we'll see whether this is still true in 6-12 months)
orbis-tertius··on On Being an Engineer in 2026
Maybe hardware? Agents workflow design? Faster/more accurate models? Using our preferences to decide what to build and our agency to actually do it (poetically speaking, being the gradient in the agent optimisation process) ?

I don't know! But maybe that's how it feels like to be far from excellence again; maybe that's how it feels like to be out of our depth again, just like we were at the beginning of our career?

I don't want to risk stretching the analogy too far, and it might be that agents make all cognitive work obsolete. But surely there'll be something that defines a capability frontier? The alternative position is to believe that there just won't be a frontier anymore (I guess that's the RSI/AGI/ASI position :shrug)

orbis-tertius··on Jane Street: Socratic Tutor
I love the idea but Jane Street might have copied (or independently rediscovered) https://github.com/bevibing/socrates-skill
orbis-tertius··on When Will We Stop Reading Code?
We might be already past the point where agents understand code better than the best developer, and they certainly are more efficient. We still want to feel like we're in control and have a grasp of what's going on, but it does seems like we are becoming the bottleneck. We're moving one abstraction layer up and only focusing on architecture/design, but I don't see any reason why architecture/design decisions won't also best left to agents.

Not sure what we'll be left doing: maybe agency itself (deciding to do something and prompting the agents to do it) will be the last thing to go?

orbis-tertius··on On Being an Engineer in 2026
I share this sentiment. But OTOH, if something is so easy to copy maybe we just have to accept that it's not that special anymore. Isn't excellence in a sense *defined* by ability to consistently achieve results above average? So the only consequence of the average shifting upward is the threshold for excellence shifting accordingly?

What constituted excellence a year ago is trivial and common today, so maybe excellence just shifted somewhere else, and the realization many of us are having is that our valuable skills are now just average, and the top has shifted upward?

← PreviousPage 2 of 2