Hacker News: bwat49

New comment by bwat49 in "Claude Opus 4.7 costs 20–30% more per session"

bwat49 — Fri, 17 Apr 2026 18:01:36 +0000

in copilot I find it hard to justify using opus at even 3x vs just using GPT 5.4 high at 1x

New comment by bwat49 in "ChatGPT for Excel"

bwat49 — Wed, 15 Apr 2026 22:49:31 +0000

its baffling how badly microsoft has handled copilot, this is exactly what copilot in office should have been

New comment by bwat49 in "Introduction to Obsidian"

bwat49 — Tue, 14 Apr 2026 00:38:09 +0000

no merging, they just show as sync conflicts

New comment by bwat49 in "F-15E jet shot down over Iran"

bwat49 — Fri, 03 Apr 2026 20:36:29 +0000

It does matter because oil is a global commodity, the fact that the US is a net exporter doesn't stop the prices from going up and other follow-on impacts to the global economy.

New comment by bwat49 in "F-15E jet shot down over Iran"

bwat49 — Fri, 03 Apr 2026 19:36:33 +0000

the big difference with Iran is the strait of hormuz. It doesn't matter how "well" it goes if it stays closed and torpedos the global economy

> inconsistent communication

I feel like "inconsistent communication" is putting it lightly, with trump going back and forth between "we won", "we'll take the oil", and "whatever we'll leave" often within the same day.

New comment by bwat49 in "Windows 11 after two decades of macOS: okay, but also awful"

bwat49 — Fri, 13 Mar 2026 22:59:44 +0000

I haven't had issues with malware since windows vista

New comment by bwat49 in "GPT-5.4"

bwat49 — Fri, 06 Mar 2026 01:19:55 +0000

yeah claude is great... but only if you pay $100-$200 a month

New comment by bwat49 in "Don't make me talk to your chatbot"

bwat49 — Tue, 03 Mar 2026 23:12:00 +0000

Yeah a trend that I've noticed in online comments is people taking LLM generated text and just removing punctuation and making it all lowercase. It's like dude, it's still so obvious xD

New comment by bwat49 in "GLM-5: Targeting complex systems engineering and long-horizon agentic tasks"

bwat49 — Wed, 11 Feb 2026 22:43:47 +0000

> Your objective has explicit instruction that car has to be present for a wash.

Which is exactly how you're supposed to prompt an LLM, is the fact that giving a vague prompt gives poor results really suprising?

New comment by bwat49 in "Simplifying Vulkan one subsystem at a time"

bwat49 — Tue, 10 Feb 2026 20:00:51 +0000

not to mention the OP mentioned 22 LTS which isn't even the most current LTS

New comment by bwat49 in "UEFI Bindings for JavaScript"

bwat49 — Mon, 09 Feb 2026 15:06:20 +0000

Your scientists were so preoccupied with whether or not they could, they didn't stop to think if they should!

New comment by bwat49 in "LLMs as the new high level language"

bwat49 — Sun, 08 Feb 2026 23:24:38 +0000

I feel so attacked right now

New comment by bwat49 in "Microsoft open-sources LiteBox, a security-focused library OS"

bwat49 — Fri, 06 Feb 2026 21:17:05 +0000

the $10 plan makes a great backup to claude or codex and the inline completions are nice

New comment by bwat49 in "Two kinds of AI users are emerging"

bwat49 — Mon, 02 Feb 2026 15:02:31 +0000

I think there's some middle ground possible between those two black and white groupings

New comment by bwat49 in "Two kinds of AI users are emerging"

bwat49 — Mon, 02 Feb 2026 01:55:38 +0000

yeah I actually use AI a lot, but copilot is... useless. When microsoft adds copilot to their various apps they don't seem to put any thought/effort behind it beyond sticking a copilot button somewhere.

And if the copilot button does nothing but open a chat window without any real integration with the app, what the hell is the point of that when there's already a copilot button in the windows taskbar?

New comment by bwat49 in "After two years of vibecoding, I'm back to writing by hand [video]"

bwat49 — Sat, 24 Jan 2026 17:22:24 +0000

> there is pressure to ship crappy code

this is true with or without AI

New comment by bwat49 in "AI Usage Policy"

bwat49 — Fri, 23 Jan 2026 14:09:42 +0000

I would hope that actually testing the changes is done regardless of whether or not AI is used

New comment by bwat49 in "Show HN: I quit coding years ago. AI brought me back"

bwat49 — Mon, 19 Jan 2026 15:55:10 +0000

LLMs are far more flexible in what you can create, opening up many niche use cases for non programmers (or those with very limited programming experience).

For example, I use LLMs for one specific thing, making plugins for an app I use (which need to be written in javascript/typescript). No code tools wouldn't be of any use to me here.

No code tools put you in a box that limits what you can create, whereas LLMs allow you to code pretty much anything (though of course how far you can get does depend on having at least some technical ability/knowledge).

New comment by bwat49 in "GLM-4.7: Advancing the Coding Capability"

bwat49 — Tue, 23 Dec 2025 15:05:29 +0000

in antigravity gemini sometimes inserts its CoT directly into code comments lol

New comment by bwat49 in "The "confident idiot" problem: Why AI needs hard rules, not vibe checks"

bwat49 — Mon, 08 Dec 2025 17:32:59 +0000

its so easy to accidentally hit enter though lol, I usually type larger prompts in my notes and copy paste then finished