Hacker News: draftsman

New comment by draftsman in "RuneScape Bench: MMOs for Agents [video]"

draftsman — Tue, 20 Oct 2026 00:32:02 +0000

Have you ever done RuneScape’s quests? No way an AI could create something so original

New comment by draftsman in "Cf: The Agentic CLI for the Cloudflare API"

draftsman — Tue, 29 Sep 2026 05:00:15 +0000

Scratching my head too. The thing is, the industry as whole is enabling this type of behavior

New comment by draftsman in "AI Has No Wisdom and Neither Will You"

draftsman — Tue, 22 Sep 2026 15:12:53 +0000

Saying you do those things when it’s AI doing them for you is akin to saying I cooked a meal while picking up fast food in a drive through line.

New comment by draftsman in "AI Has No Wisdom and Neither Will You"

draftsman — Tue, 22 Sep 2026 15:05:24 +0000

That is where a lot of people in tech believe things are headed, executives in particular. Fully autonomous AI-driven codebases. “Dark factories.” One agent generating a plan, one writing the code, one responsible for testing and validating, and one to orchestrate the rest. The idea is software development will follow in the footsteps of physical manufacturing and eventually become fully automated. I think one huge flaw with this belief/comparison is that the automated assembly line is deterministic. LLMs and AI agents are not. Every Tacoma made on the Toyota assembly line is made from the same blueprint. There are no robots deciding on-the-fly whether to use a laser weld or an adhesive, what material to use for a specific component, etc. Now think about how LLMs build software. No matter how strict a harness or detailed spec you give it, it will always make decisions. That is what makes it “agentic” after all.

New comment by draftsman in "AI Has No Wisdom and Neither Will You"

draftsman — Tue, 22 Sep 2026 14:48:22 +0000

Not trying to come at you, but what is stopping you from educating the juniors at your company?

New comment by draftsman in "Born Against, or why hobby programming communities are against LLM usage"

draftsman — Thu, 06 Aug 2026 05:39:18 +0000

Writing code without an LLM is akin to cooking a meal yourself, as opposed to something in between hiring a private chef and pulling a slot machine lever. When I cook a meal for myself or my loved ones, I become deeply familiar with the ingredients and the recipe. I am a good cook. Every decision, small and large, I make myself. Using feedback, I can tweak the components and the process. However, if I order food and call it my own creation, I’ll be speechless when my nut-allergic friend asks me if I used peanut oil or olive oil. And does it taste good? The end result is subjective, not binary, like your three similes. What if the food sucks? Must I now micromanage the chef? I don’t want to make them cook it again and again, hoping each time it’ll taste little more like how I want it to. I’d rather just cook it myself; I am a good cook, afterall.

New comment by draftsman in "The AI Aesthetic"

draftsman — Fri, 31 Jul 2026 02:29:27 +0000

Specifically, AI loves to separate headers with //

New comment by draftsman in "I used Claude Code to get a second opinion on my MRI"

draftsman — Mon, 29 Jun 2026 13:33:00 +0000

May I ask, is the hypermobility disorder you refer to EDS? If so, what was the injury?

New comment by draftsman in "Please Use AI"

draftsman — Fri, 29 May 2026 15:14:34 +0000

You’ve either willfully ignored the point, or completely missed it as it flew over your head. AI wants to replace “your friend” completely.

New comment by draftsman in "Please Use AI"

draftsman — Fri, 29 May 2026 15:08:23 +0000

I find very little joy in trying to wrangle the blackboxes that are LLMs. The undeterministic nature of them frustrates me, and feels nothing like the software engineering I know and love. However, I know I’m in the minority here, as almost everyone else in the industry I’ve talked to seems to love using them.

New comment by draftsman in "The Art of Money Getting"

draftsman — Sat, 23 May 2026 17:16:09 +0000

Do you find joy in using LLMs to write software? I tried using Claude/Cursor/CodeX/etc. for personal projects and experimentation, and I found no joy in it. I learned nothing, and when my MVPs were complete, I only had a shallow understanding of how the code that powered them worked.

New comment by draftsman in "The last six months in LLMs in five minutes"

draftsman — Tue, 19 May 2026 15:58:20 +0000

And there’s good reason for that. Anthropic, OpenAI, Salesforce, and so on have aggressively marketed LLMs as better than humans at working. It’s no surprise when we find out something is build using an LLM, we expect it to match the marketing.

New comment by draftsman in "Eric Schmidt speech about AI booed during graduation"

draftsman — Mon, 18 May 2026 13:14:02 +0000

Do you have a source for your “millions” claim? Every source I can find says there are somewhere between 60 and 70 thousand immigrants currently in detention centers, based on internal ICE data. That’s still a fuck-ton of people to cage up, there’s no need to hyperbolize.

New comment by draftsman in "Cloudflare to cut about 20% of its workforce"

draftsman — Fri, 08 May 2026 13:03:27 +0000

> More productivity means fewer people are required.

Required for what? If your goal is growth, and AI really is improving productivity of every employees that uses it, then why would you fire anyone?

New comment by draftsman in "Cloudflare to cut about 20% of its workforce"

draftsman — Fri, 08 May 2026 12:56:52 +0000

Unfortunately I think we’ll see more and more of this as companies continue to encourage their employees to use LLMs everywhere and for everything. Eventually they will have to come to terms with the cost of such mandates, and it’s either ask your employees to “use AI less,” or it’s let some percentage go and continue to let the rest burn tokens.

New comment by draftsman in "Today I've made the difficult decision to reduce the size of Coinbase by ~14%"

draftsman — Tue, 05 May 2026 17:19:00 +0000

Your comment reminded me that this still happens in the NBA. At 43 years old, Udonis Haslem seldom played minutes towards the end of his 20 year career with the Heat. But they kept him on as a “player-coach,” in that he was a mentor to the younger players and assisted in their coaching. Kyle Lowry is another current example of this “player-coach” role, currently on the Sixers.

New comment by draftsman in "I quit drinking for a year"

draftsman — Tue, 28 Apr 2026 12:48:27 +0000

Conversely, I started after Calude Code.

1. The thought of slop everywhere is too much 2. I no longer need to be sober to build software

New comment by draftsman in "I'm OK being left behind, thanks"

draftsman — Sun, 22 Mar 2026 04:08:12 +0000

And more importantly, think of the funding we’ll get

New comment by draftsman in "I'm OK being left behind, thanks"

draftsman — Fri, 20 Mar 2026 14:21:20 +0000

LLMs have lowered the bar for the unskilled person to create shit software. I have used Opus 4.6 on a number of projects, and it still spits out buggy, and sometimes, flat out broken code. I was actually surprised when it completely hallucinated the names of query params for an HTTP request in my code, when in the prompt I had explicitly given it the exact names it needed to use. I thought these frontier models were supposed to be game changing.

New comment by draftsman in "AirPods Max 2"

draftsman — Tue, 17 Mar 2026 03:08:22 +0000

I hope that commenter was being hyperbolic. I have heard of headphones making visible impressions or “dents” in the soft tissue and msucle after long periods of use (Google Tyler1 headphone dent if you don’t believe me), but such a dent would disappear within minutes or hours. An actual deformation of the skull due to headphone-wearing would definitely be strange.