Hacker News: dominotw

New comment by dominotw in "LLMs are eroding my software engineering career and I don't know what to do"

dominotw — Sun, 07 Jun 2026 13:23:37 +0000

This has been said millions of times but yet you felt the need to say this again. maybe our jobs are safe :)

New comment by dominotw in "LLMs are eroding my software engineering career and I don't know what to do"

dominotw — Sun, 07 Jun 2026 13:21:49 +0000

funny i was able to do all my taxes this year with ai help and not needing accountant.

New comment by dominotw in "LLMs are eroding my software engineering career and I don't know what to do"

dominotw — Sun, 07 Jun 2026 13:21:06 +0000

you dont need to vibe code shitty apps. you just need to learn how to use apps like codex, claude desktop.

New comment by dominotw in "I design with Claude more than Figma now"

dominotw — Sun, 07 Jun 2026 13:09:48 +0000

thats really sad that only way you can understand something is with pictures and demos. like a little toddler.

when they already come up with a working model it doesnt really leave any room for abstract thought because now you are in concerte world . They see you as a machine that turns mocks into impls ( maybe you youself see yourself like that).

its ok if you see yourself as a code monkey monkey doing menial job of implementing someones mockup. But that job wont be here long and you will be on the streets holding "can turn working mocks to production code for food" signs.

honestly your attitude scares me more than some business guy building crap in lovable.

New comment by dominotw in "Arithmetic Without Numbers – How LLMs Do Math"

dominotw — Sun, 07 Jun 2026 13:07:24 +0000

i dont like this new trend of generating html with ai to say something. i think some guy from anthropic started this trend .

now everything looks the same and i can no longer read on kindle.

New comment by dominotw in "Ask HN: Why is the HN crowd so anti-AI?"

dominotw — Sat, 06 Jun 2026 20:25:39 +0000

>but do people realize that code is just a means to an end?

yes but then why do you need programmers to sit in between users and ai when ai can generate code on the fly and give users what they want

New comment by dominotw in "Nvidia is proposing a beast of a CPU system for Windows PCs"

dominotw — Sat, 06 Jun 2026 20:12:27 +0000

dont want to share my pics with "cloud services"

New comment by dominotw in "How LLMs work"

dominotw — Sat, 06 Jun 2026 13:18:17 +0000

> Over the next month I ended up drawing out a block diagram on a whiteboard I have in my office, with the math involved next to each step in the blackboard. I’d puzzle about each step along the way, and the triumph of completing the drawing was also that of this sense of deep understanding. I kept that drawing up for many months after, and would gaze at it often during meetings and idle moments in wonder.

how did you know about the steps and there was math involved. i am curious about your process and you came up with what exactly to learn to unravel the mystery.

New comment by dominotw in "Sakana AI's Recursive Self-Improvement (RSI) Lab"

dominotw — Fri, 05 Jun 2026 20:52:44 +0000

recursive self-hype

New comment by dominotw in "My Agent Skill for Test-Driven Development"

dominotw — Fri, 05 Jun 2026 20:41:41 +0000

even if that works one time you can never be sure that your customization is in place or fell out of context's important zone or is contradicted by later context . you've reverted back to base llm behavior.

you are treating skill like sure thing

New comment by dominotw in "My Agent Skill for Test-Driven Development"

dominotw — Fri, 05 Jun 2026 20:35:51 +0000

i think gp is calling skills snakeoil in genral

New comment by dominotw in "My Agent Skill for Test-Driven Development"

dominotw — Fri, 05 Jun 2026 20:18:54 +0000

i belive gp means llms produce what they see in training data/rl there isnt much too much customization you can do with skills.

they are being sold as more powerful than they are. Like llms are intelligent blank slates that can be customized with mere markdown files.

New comment by dominotw in "I'm skeptical about efforts to revolutionize schooling"

dominotw — Fri, 05 Jun 2026 18:21:23 +0000

comment is competely devoid of any logic or facts. pure emotion.

New comment by dominotw in "Open Code Review – An AI-powered code review CLI tool"

dominotw — Fri, 05 Jun 2026 14:20:50 +0000

well they are different. human or not. so it makes sense to get it reviewing by "something" different that one that wrote code.

New comment by dominotw in "AI, Ashby Engineering, and the future"

dominotw — Thu, 04 Jun 2026 20:33:56 +0000

where did it come out of all of sudden. they must have a killer sales dept

New comment by dominotw in "The desperation of NYTimes"

dominotw — Thu, 04 Jun 2026 18:10:11 +0000

gp's comment had nothing to do with value of the publication. are you implying it ok for them to do that because value?

And making it hard to cancel is not just "marketing" . There are even laws to prevent that sort of thing.

New comment by dominotw in "Claude Code and Codex can have real-time conversation via Git"

dominotw — Thu, 04 Jun 2026 12:01:01 +0000

can this be used to launch subagents in tmux

New comment by dominotw in "Claude Code and Codex Can Have Real-Time Conversation via Git"

dominotw — Thu, 04 Jun 2026 11:59:17 +0000

or via humans communicating via slack. happeneing all over workplaces.

New comment by dominotw in "GitHub Copilot App"

dominotw — Tue, 02 Jun 2026 19:43:26 +0000

copilot had such a lead when this whole ai coding thing started. what happened?

New comment by dominotw in "Alphabet announces $80B equity capital raise to expand AI infra and compute"

dominotw — Tue, 02 Jun 2026 13:12:22 +0000

so the argument here is that its too niche for google to care ? i dont belive that they made explicit decision to make a lame version of claude code that their own devs dont use.