Hacker News: bulletsvshumans

New comment by bulletsvshumans in "Linux 7.1"

bulletsvshumans — Mon, 15 Jun 2026 01:53:57 +0000

New comment by bulletsvshumans in "I returned to AWS and was reminded why I left"

bulletsvshumans — Sun, 10 May 2026 13:51:34 +0000

They absolutely could calculate and put the price in the UI if they wished to. Other cloud vendors do.

New comment by bulletsvshumans in "ChatGPT Images 2.0"

bulletsvshumans — Tue, 21 Apr 2026 23:21:40 +0000

Democratizing visual communication is arguably useful, for instance helping people to create diagrams that illustrate a concept they wish to convey. This is contingent on the tech working sufficiently well that the visuals are more effective at communication than the text that went into producing them though.

New comment by bulletsvshumans in "ChatGPT Images 2.0"

bulletsvshumans — Tue, 21 Apr 2026 23:16:39 +0000

This is also a stylistic choice that the New Yorker magazine uses for words with double vowels where you pronounce each one separately, like coöperate, reëlect, preëminent, and naïve. So possibly intentional.

New comment by bulletsvshumans in "Uncharted island soon to appear on nautical charts"

bulletsvshumans — Sun, 12 Apr 2026 23:08:45 +0000

Dibs

New comment by bulletsvshumans in "Why AI Sucks at Front End"

bulletsvshumans — Sun, 12 Apr 2026 15:28:01 +0000

One thing that helps with #2 ('It cannot see') -- Try playwright-cli. Your agent can use it to inspect the DOM, see what styles are applied to elements, simulate clicks, etc.

New comment by bulletsvshumans in "The team behind a pro-Iran, Lego-themed viral-video campaign"

bulletsvshumans — Wed, 08 Apr 2026 00:08:39 +0000

I presume U.S. Western allies

New comment by bulletsvshumans in "Agent-to-agent pair programming"

bulletsvshumans — Fri, 27 Mar 2026 14:33:25 +0000

I had a prototype where the agent primarily worked autonomously, and it could solicit human feedback via tool calls. But yes that pattern does feel like it is hastening the apocalypse.

New comment by bulletsvshumans in "Pentagon formally labels Anthropic supply-chain risk"

bulletsvshumans — Sat, 07 Mar 2026 13:35:38 +0000

Either way, you can walk through the door after. Unless we reseal it legislatively. Resetting norms may be a lost cause at this point.

New comment by bulletsvshumans in "Gemini 3 Deep Think drew me a good SVG of a pelican riding a bicycle"

bulletsvshumans — Sat, 14 Feb 2026 20:06:46 +0000

They rigged it.

New comment by bulletsvshumans in "Gradient.horse"

bulletsvshumans — Sat, 14 Feb 2026 00:41:31 +0000

Ok I bought my dumb horse on a mug, I admit it.

New comment by bulletsvshumans in "Claude's new constitution"

bulletsvshumans — Thu, 22 Jan 2026 00:37:18 +0000

The constitution gives a number of examples. Here's one bullet from a list of seven:

"Provide serious uplift to those seeking to create biological, chemical, nuclear, or radiological weapons with the potential for mass casualties."

Whether it is or will be capable of this is a good question, but I don't think model trainers are out of place in having some concern about such things.

New comment by bulletsvshumans in "Luxury Yacht is a desktop app for managing Kubernetes clusters"

bulletsvshumans — Mon, 19 Jan 2026 20:10:30 +0000

I see we have entered the "Gas Town" naming era.

New comment by bulletsvshumans in "Show HN: Nogic – VS Code extension that visualizes your codebase as a graph"

bulletsvshumans — Tue, 13 Jan 2026 23:21:47 +0000

Please publish to Open VSX so it is easily available for VS Code forks like Cursor as well.

New comment by bulletsvshumans in "ASCII-Driven Development"

bulletsvshumans — Sat, 10 Jan 2026 21:10:28 +0000

I think this a good technique to be familiar with, although in a lot of situations I've achieved similar value by simply feeding the underlying JSON data objects corresponding to the intended UI state back into the coding agent. It doesn't render quite as nicely, but it is often still human-readable, and more importantly both LLM and procedurally interpretable, meaning you can fold the results back into your agentic (and/or conventional testing) development loop. It's not quite as cool, but I think a bit more practical, especially for earlier stage development.

New comment by bulletsvshumans in "A spider web unlike any seen before"

bulletsvshumans — Mon, 05 Jan 2026 12:42:23 +0000

Maybe the glut of conventional food leaves the prospect of eating their compatriots less appetizing.

New comment by bulletsvshumans in "Microsoft kills official way to activate Windows 11/10 without internet"

bulletsvshumans — Sat, 03 Jan 2026 02:44:18 +0000

Keep milking the cash cows to pay for the new growth area (AI). Convert maximum % of Windows users into subscription service consumers (e.g. cloud storage, Office 365, future paid AI capabilities.)

New comment by bulletsvshumans in "The 70% AI productivity myth: why most companies aren't seeing the gains"

bulletsvshumans — Tue, 30 Dec 2025 15:29:28 +0000

I think coding agents require fundamentally different development practices in order to produce efficiency improvements. And just like any new tool, they benefit from wisdom in how they are applied, which we are just starting to develop as an industry. I expect that over time we will grow to understand and also expand the circumstances in which they are a net benefit, while also appreciating where they are a hindrance, leading to an overall efficiency increase as we avoid the productivity hit resulting from their misapplication.

New comment by bulletsvshumans in "Publishing your work increases your luck"

bulletsvshumans — Sat, 27 Dec 2025 04:34:35 +0000

Hello fellow human!

New comment by bulletsvshumans in "Ask HN: How can I get better at using AI for programming?"

bulletsvshumans — Sat, 13 Dec 2025 20:13:29 +0000

Try specification-driven-development with something like speckit [0]. It helps tremendously for facilitating a process around gathering requirements, doing research, planning, breaking into tasks, and finally implementing. Much better than having a coding agent just go straight to coding.

[0] - https://github.com/github/spec-kit