Hacker News: sosuke

New comment by sosuke in "Google Chrome's Next Update Will Mark the End of Popular Ad Blockers"

sosuke — Tue, 16 Jun 2026 16:30:52 +0000

Just an FYI there are many efforts already available to clean and or provide a clean Firefox.

To Read a Book, to Collect a Book

sosuke — Thu, 28 May 2026 15:41:44 +0000

Article URL: https://sosuke.com/to-read-a-book-to-collect-a-book/

Comments URL: https://news.ycombinator.com/item?id=48310593

Points: 3

# Comments: 0

New comment by sosuke in "You Can Start Building LLM Skills Before You Know the Whole Shape"

sosuke — Tue, 26 May 2026 17:14:19 +0000

I leaned into the narrative style for this post. The content comes from my concrete talks and work but I don't mention any specifics. Not sure if I like the result but it was still interesting. The topic was light and easy enough I don't feel it suffered for it.

You Can Start Building LLM Skills Before You Know the Whole Shape

sosuke — Tue, 26 May 2026 17:14:19 +0000

Article URL: https://sosuke.com/you-can-start-building-llm-skills-before-you-know-the-whole-shape/

Comments URL: https://news.ycombinator.com/item?id=48282663

Points: 8

# Comments: 1

Models Have Blind Spots: Debugging Unfamiliar Code with a Multi-LLM Loop

sosuke — Tue, 26 May 2026 02:41:51 +0000

Article URL: https://sosuke.com/models-have-blind-spots-debugging-unfamiliar-code-with-a-multi-llm-loop/

Comments URL: https://news.ycombinator.com/item?id=48274372

Points: 1

# Comments: 0

Bone Keeper AI Assisted Feature Film

sosuke — Sun, 24 May 2026 21:54:59 +0000

Article URL: https://sosuke.com/bone-keeper-ai-assisted-feature-film/

Comments URL: https://news.ycombinator.com/item?id=48261396

Points: 3

# Comments: 0

New comment by sosuke in "AI is just unauthorised plagiarism at a bigger scale"

sosuke — Thu, 21 May 2026 14:41:08 +0000

I'll bite. I have always been told copyright is inherit. Does it cost money to file a copyright? Do I need to do it for each blog post? For each gist? I'll totally setup some scripts to make it happen if it what actually needs doing to have the copyright I expected.

Edit: remember not to down vote ideas you disagree with. I think it was only down vote things that lower the discourse

The Workflows I Created Using LLMs Became My Ecosystem

sosuke — Wed, 06 May 2026 04:07:43 +0000

Article URL: https://sosuke.com/my-personal-skill-creation-orchestration-and-persona-prompting-workflows-i-created-using-llms-became-my-ecosystem/

Comments URL: https://news.ycombinator.com/item?id=48032054

Points: 3

# Comments: 0

New comment by sosuke in "Show HN: Agent Historic Philosophical Persona Routing and Prompts"

sosuke — Tue, 05 May 2026 01:16:14 +0000

It's a competitive world out there isn't it? Thank you

Show HN: Agent Historic Philosophical Persona Routing and Prompts

sosuke — Tue, 05 May 2026 00:02:24 +0000

I've been building this for a while. The core of it is I've assigned different tasks in a software engineering job to different philosophers. The prompts are written toward their thinking by "them" but the keywords are generic. I absolutely love using this prompt system. I share it every chance I get. I wrote a whitepaper about it. Maybe ya'll would be interested in it. I find my experience is better with my prompts than without.

The only thing you might not like is my heavy handed treatment of logging output. I was seriously fed up with LLMs trying to run huge tests or scripts and then looking at just the last 20 characters. Everything is logged out to files and then the files are queried for the answers it wants.

Comments URL: https://news.ycombinator.com/item?id=48016503

Points: 5

# Comments: 2

New comment by sosuke in "Ghostmoon.app – The Swiss Army Knife for your macOS menu bar"

sosuke — Mon, 30 Mar 2026 13:03:49 +0000

Unrelated to the app but I dig your website design.

New comment by sosuke in "I was interviewed by an AI bot for a job"

sosuke — Thu, 12 Mar 2026 06:43:24 +0000

This was a thing in the beginning of 2025. Not sure how they do now but I did the interview just to see the AI bot in action. It wasn't great but it was amazing at the same time. It might have been around sooner but I remember doing one AI interview that had a video lip synced avatar asking questions like we were on video chat.

New comment by sosuke in "A new Google model is nearly perfect on automated handwriting recognition"

sosuke — Sat, 15 Nov 2025 01:16:24 +0000

Doing something novel is incredibly difficult through LLM work alone. Dreaming, hallucinating, might eventually make novel possible but it has to be backed up be rock solid base work. We aren't there yet.

The working memory it holds is still extremely small compared to what we would need for regular open ended tasks.

Yes there are outliers and I'm not being specific enough but I can't type that much right now.

New comment by sosuke in "Show HN: I scraped 3B Goodreads reviews to train a better recommendation model"

sosuke — Fri, 07 Nov 2025 16:51:46 +0000

Feature request: Combine book series into a single entity. Bummer getting recommendations for another book in the same series as one I already liked and read.

Feature request: Exclude books already in shelf. This is harder I'm sure. I've got 1146 books in my Read shelf.

New comment by sosuke in "Reading for pleasure plummets by 40% in the US"

sosuke — Mon, 25 Aug 2025 23:01:19 +0000

I know a couple folks that do a ton of phone only reading now. I haven't read for pleasure in over a decade but I've listened to ~1300 different audiobooks. Seems like this isn't well thought out.

New comment by sosuke in "Apple unveils new Mac Studio, the most powerful Mac ever, featuring M4 Max"

sosuke — Wed, 05 Mar 2025 16:27:25 +0000

I don't know what I'm talking about but when I first asked your question this https://gist.github.com/Artefact2/b5f810600771265fc1e3944228... helped start me on a path to understanding. I think.

But if you don't already know the question your asking is not at all something I could distill down into a sentence or to that would make sense to a lay-person. Even then I know I couldn't distill it at all sorry.

Edit: I found this link I referenced above on quantized models by bartowski on huggingface https://huggingface.co/bartowski/Qwen2.5-Coder-14B-GGUF#whic...

New comment by sosuke in "ASTRA: HackerRank's coding benchmark for LLMs"

sosuke — Tue, 11 Feb 2025 22:48:30 +0000

No huggingface models or did I just miss them? Edit: they mention doing open models at some point at the bottom of the page

New comment by sosuke in "Ask HN: Who wants to be hired? (February 2025)"

sosuke — Mon, 03 Feb 2025 19:04:05 +0000

  Location: Austin, TX
  Remote: Preferred remote but all things are negotiable
  Willing to relocate: Not really
  Technologies: JavaScript, TypeScript, Node, GIT, NPM, React, Web Components, Webpack, Build configuration, Jest, Mocha, ESLint, CSS, SASS, Storybook, Monorepo configuration, TestCafe, Unit testing, End-to-end testing, Integration testing, Backbone, Marionette, jQuery, Bootstrap, Google MUI React UI Components, MySQL, Postgres SQL, SQL Server, C#, Python, Ruby, Rake, Docker, TeamCity, Jenkins, Amazon Web Services, Terraform, PowerShell, Visual Studio, EC2, S3, DynamoDB, Lambda, API Gateway, Cloud Development Kit, EC2 Image Builder, HTML, Internationalization i18n, Localization l10n, Visual Diff testing, Bash scripting, Objective-C, Android Java, Cordova, KendoUI, Flash, Flex, ActionScript
  Résumé/CV: https://barrettsonntag.com/Sonntag_Barrett_resume.pdf
  Email: barrett@sosuke.com

Is it better that I list everything or just a few things? I'm always conflicted. What if I said TypeScript and React but left out JavaScript? That could mean I never worked with JavaScript right? Which sounds crazy but code camps produce React developers that have no experience outside that framework.

New comment by sosuke in "Emotional support across adulthood: A 60-year study of men’s social networks"

sosuke — Sat, 25 Jan 2025 19:53:30 +0000

Imagine three other possibilities:

You have a dozen people who would give you emotional support but you don't ask for any because you aren't sure you could give emotional support in return.

You have a dozen people you think might give you emotional support but you don't want to burden them with your problems.

You have a dozen people that would give you emotional support, maybe once, but you are too afraid to burn the single emotional support coupon until its more important.

New comment by sosuke in "MIT study explains why laws are written in an incomprehensible style"

sosuke — Tue, 17 Dec 2024 07:03:39 +0000

It’s awesome they try to define those terms. But I wouldn’t call that well defined at all. https://www.lexology.com/library/detail.aspx?g=6a4c20dc-594d...

I would say that math is unambiguous.

Measurements are becoming more unambiguous. The accepted measurement of a kilogram equalling s Avogadro’s constant. Something like the number of silicon atoms in a 93mm sphere?

But the definitions of best and reasonable are only accepted based off precedent and we’ve seen in recent history precedent in law isn’t as reliable or defined as we may have thought.

Is there any language or any level of language that can remain defined across time and culture?

So long as legalese requires interpretation to determine intent and outcome it can be expected be incomprehensible.