Hacker News: ubercore

New comment by ubercore in "AI outperforms law professors in Stanford Law study"

ubercore — Wed, 03 Jun 2026 12:50:54 +0000

Agreed, and it's the same in software. Probably the biggest time-sink right now as a tech lead is people going from idea to fully-fleshed-out PR, and then having to go back to have a discussion of "was this the right thing to do". It causes frustration all around (being a "no" much more, and having someone tell you your finished work isn't valuable).

New comment by ubercore in "macOS needs its grid back"

ubercore — Tue, 02 Jun 2026 09:49:33 +0000

I make a version of this happen with Aerospace on macOS.

New comment by ubercore in "Using Git's rerere feature to escape recurring conflict hell"

ubercore — Mon, 01 Jun 2026 13:43:03 +0000

I've never even seen someone suggest a rebase master onto feature workflow! TIL.

New comment by ubercore in "ATLAS: Autoformalized Textbook Library At Scale"

ubercore — Fri, 29 May 2026 20:29:01 +0000

Didn't read the article, sorry, but this reminds me we _really_ need more cool acronyms back in our industry.

New comment by ubercore in "The dead economy theory"

ubercore — Fri, 29 May 2026 20:28:23 +0000

You haven't used messenger much then, if you're comparing the complexity of the two.

New comment by ubercore in "Investigating how prompt politeness affects LLM accuracy (2025)"

ubercore — Thu, 28 May 2026 13:48:58 +0000

I love this angle as people learn how to interact with LLMs. Doesn't matter what the LLM is, we are still people and I think there are consequences to shoveling rudeness at a thing that talks to you like another person!

New comment by ubercore in "Dropbox CEO Drew Houston to step down"

ubercore — Wed, 27 May 2026 11:11:31 +0000

Yes, this is one of the most ineffective parts of public trading. It's impossible to say what the leadership here would have done without such _wild_ changes in the surrounding environment. While I understand the argument that in the end it doesn't matter, companies should find the way to succeed regardless, I think it causes a lot of good leadership to be lost, or a lot of bad decisions leading to local minima.

New comment by ubercore in "Hershey Bets on Agentic AI to Rethink $2B in Marketing Spend"

ubercore — Mon, 18 May 2026 13:19:34 +0000

They could, easily, but then it wouldn't taste like Hershey's chocolate and people don't like that.

New comment by ubercore in "How Claude Code works in large codebases"

ubercore — Fri, 15 May 2026 08:14:50 +0000

The tokens it uses up clarifying can be saved, and it's often good to write out intentions. For instance, you may be mid-process on cleaning up some architectural pattern, and giving it guidance about where to find docs to follow, etc, are very project-specific.

New comment by ubercore in "Local AI needs to be the norm"

ubercore — Mon, 11 May 2026 09:31:05 +0000

The conspiracy angle here is not really relevant. Ram is expensive and they're gearing up for M5 studios. Not the illuminati keeping better LLM models out of your hands.

New comment by ubercore in "Valve releases Steam Controller CAD files under Creative Commons license"

ubercore — Thu, 07 May 2026 10:45:26 +0000

Dropping half life is the biggest sin, and I will never forgive them.

New comment by ubercore in "Parallel agents in Zed"

ubercore — Thu, 23 Apr 2026 12:03:08 +0000

Yeah, first thing I did was change all the locations back. I really dislike the automatic layout change they pushed.

Also, watching the change notes, most effort seems to be focused on agents this days, which is a bit worrying. I love Zed because it's great editor that also knows a bit about agents; I don't want it to continue pivoting towards pushing agent management deeper and deeper into the experience.

New comment by ubercore in "Show HN: Broccoli, one shot coding agent on the cloud"

ubercore — Wed, 22 Apr 2026 21:39:15 +0000

We don't have this kind of tooling built up, but we've been using Linear as a source of truth alongside a human written prompt adding context. It's worked really well for both feature development and bug hunting, and helps keep us honest with tickets (good LLM context is still good human context) as well as maintain some level of consistency between LLM passes on the same issue.

New comment by ubercore in "Another Day Has Come"

ubercore — Wed, 22 Apr 2026 18:55:57 +0000

Yeah it seems to be really up to individual experience. I had two apple-made lightning cables that shorted and burned out the leads on the male end of the connector.

New comment by ubercore in "Another Day Has Come"

ubercore — Wed, 22 Apr 2026 15:53:28 +0000

I've never had trouble with usb-c, but have had lightning connectors short out and burn one of the leads, or stop working from dust. Not sure I'd say one is better than the other, but individual experience can really vary on these kind of things. Tough to say one is clearly better imo.

New comment by ubercore in "Another Day Has Come"

ubercore — Wed, 22 Apr 2026 15:48:15 +0000

Same type of concerns were raised about usb-c: more dust collects, worse connector design, would make the phones too thick, etc etc.

New comment by ubercore in "GitHub CLI now collects pseudoanonymous telemetry"

ubercore — Wed, 22 Apr 2026 14:02:29 +0000

It makes me think, what `gh` features don't generate some activity in the github API that could as easily guide feature development without adding extra telemetry?

New comment by ubercore in "Acetaminophen vs. ibuprofen"

ubercore — Wed, 22 Apr 2026 13:49:32 +0000

American in Norway, it's always amusing when I buy some Ibux at the pharmacy, and get questioned about it and steered towards Paracet instead.

New comment by ubercore in "Another Day Has Come"

ubercore — Wed, 22 Apr 2026 13:43:32 +0000

Didn't the Apple Faithful say the same for usb-c?

New comment by ubercore in "John Ternus to become Apple CEO"

ubercore — Mon, 20 Apr 2026 21:30:47 +0000

I know it is actually AI, but calling Siri AI vs the current state of the art is... generous.