Hacker News Reader

syndackson Ask HN: Who wants to be hired? (February 2026)

  Location: NYC, New York, Brooklyn, Queens
  Remote: Sure, or hybrid
  Willing to relocate: Yea
  Technologies: Python, Js, Go, PHP, React, Django, and more
  Résumé/CV: https://www.linkedin.com/in/dacks-m-9451428a/
 
  About: I'm a hands-on engineering leader who builds teams that ship products and drive revenue. At Quizlet, I led a 30-person org across Ads and Growth, scaling advertising revenue from $20M to $50M+. Before that, I was CTO at Slader, where I grew the engineering team from 3 to 14 and led the company through its acquisition by Quizlet. I'm happy to be hands-on as much as needed.

syndackson Kimi K2.5 Technical Report [pdf]

How do people evaluate creative writing and emotional intelligence in LLMs? Most benchmarks seem to focus on reasoning or correctness, which feels orthogonal. I’ve been playing with Kimmy K 2.5 and it feels much stronger on voice and emotional grounding, but I don’t know how to measure that beyond human judgment.

syndackson AI2: Open Coding Agents

LLM shit post

syndackson CLI agents make self-hosting on a home server easier and fun

Can the same thing be said for using docker compose etc on a VPS to host a web app? Ie you can get the ergonomic / ease of using Fly, Renderer?

Historically, managed platforms like Fly.io, Render, and DigitalOcean App Platform existed to solve three pain points: 1. Fear of misconfiguring Linux 2. Fear of Docker / Compose complexity 3. Fear of “what if it breaks at 2am?”

CLI agents (Claude Code, etc.) dramatically reduce (1) and (2), and partially reduce (3).

So the tradeoff has changed from:

“Pay $50–150/month to avoid yak-shaving” → “Pay $5–12/month and let an agent do the yak-shaving”

syndackson Ask HN: What kind of setup do you run for your children?

Crayons, paper, some magnatiles.

syndackson Claude Code On-the-Go

It would be a deep irony if LLMs ended up ushering in the social rupture that never arrived in the industrial era. When the pigs turn hogs and refuse to share even the scraps, they shouldn’t be surprised if the system they depend on becomes their undoing.

syndackson 2025: The Year in LLMs

I can’t get over the range of sentiment on LLMs. HN leans snake oil, X leans “we’re all cooked” —- can it possibly be both? How do other folks make sense of this? I’m not asking for a side, rather understanding the range. Does the range lead you to believe X over Y?

syndackson Get an AI code review in 10 seconds

In CC or Codex (or whichever) — “run git diff and review”

syndackson New Kindle feature uses AI to answer questions about books

100% required on all Pynchon novels that's for sure.

syndackson Launch HN: Phind 3 (YC S22) – Every answer is a mini-app

This is pretty cool!

Since we’re sharing related work, I’ve been building something at a very different layer of the stack. Shameless plug warning!

Where Phind gives you an interactive answer right now, I built SageNet for the opposite problem: when you want to go from zero → actually good at something over weeks/months, not just get a one-shot result.

SageNet:

- builds a personalized learning plan

- adapts as you progress

- generates short audio lessons

- gives real projects

- has a daily voice check-in agent

- lets you share a public progress dashboard

If anyone wants to try it: https://www.sagenet.club

syndackson Reverse engineering a $1B Legal AI tool exposed 100k+ confidential files

or, they wrote it and asked an LLM to improve the flow

syndackson Ask HN: What Are You Working On? (Nov 2025)

I've been building SageNet, a voice-first AI coach that turns your goals into structured, adaptive learning plans.

After a 2-minute voice conversation, Sage generates a personalized 6-module roadmap with build-first projects. It checks in by voice, analyzes your reflections, and regenerates your plan if needed. You can invite friends to your Support Squad for accountability.

The biggest insight so far is people don’t want “infinite content.” They want structure and someone who remembers them.

would love feedback!

http://sagenet.club

syndackson Heroin addicts often seem normal

I recommend the books Cherry or Wasting Talent for two semi-autobiographical novels that show heavy/gnarly addiction. As a non addict, it wasn’t until I read a book like these until I was able gain more empathy for the spiral. Unlike news articles or stats, these offer much more human (perhaps mildly fabricated) anecdotes of how seemingly impossible it is for addicts to get clean. I’m aware my consumption of these stories borders on “poverty porn”, while also helping me empathize with that side of the human condition.

syndackson Tariffs Are Way Up. Interest on Debt Tops $1T. and Doge Didn't Do Much

Where can one learn more about this?

syndackson MLB approves robot umpires for 2026 as part of challenge system

How did you come to that conclusion that this is a function of betting? As a baseball fan, this feels like a long overdue feature (at least in the world of video review challenge). I think it's simply going to make the game better. MLB is losing to the NFL/NBA, and they need to put out a better product.

syndackson Qwen3-Omni: Native Omni AI model for text, image and video

https://www.alibabacloud.com/help/en/model-studio/realtime?s...

syndackson Qwen3-Omni: Native Omni AI model for text, image and video

Does this support realtime speech to speech via API? If so, where is this hosted/documented? I wasn’t able to see any info. I’d love to use this in lieu of OAIs (expensive) real time speech to speech offering.

syndackson Is Your Flexible Schedule Burning You Out?

https://archive.ph/dxfFH

syndackson I built a AI transcription app because my girlfriend needed one for uni

I’m actually curious to know how you’re hosting whisper Vs say just using the OpenAI api. I’m also wondering how offloading the transcription would to the client with something like https://github.com/xenova/whisper-web

syndackson I built a AI transcription app because my girlfriend needed one for uni

Cool, I’m working on something similar. Mind me asking what stack you are using to build this?

syndackson The cultural decline of literary fiction

I also gave up on Pynchon. You should check out A Brief History of Seven Killings, postmodern done right if you ask me.

syndackson Improving recommendation systems and search in the age of LLMs

Can you share more, or at least point me in the right direction?

syndackson Show HN: SpRAG – Open-source RAG implementation for challenging real-world tasks

Hi Zach, how do you think this architecture would perform for one longer document i.e. a novel of >50k words <100k? the queries would be about that one long document as opposed to multiple documents. any tips on how to approach my use case? thanks

syndackson NPR suspends veteran editor as it grapples with his public criticism

Anyone remember how awesome This American Life was? They used to be about just that — an American [in their life] with an amazing story to tell. So simple and elegant. Then they went massively down hill around the time Trump was elected. They seemed to be “on the campaign trail” more often than not, or about some kind of grievance or “injustice”. I stopped listening.

syndackson Ask HN: Is RAG the Future of LLMs?

Are there any best practices for doing RAG over, say, a novel? (50k-100k words) things that would make this unique compared, say, RAG over smaller docs or research papers: - ability to return specific sentences/passages of a character while also keeping their arch in mind from beginning to end of story

syndackson Tell HN: GitHub is blocking search unless you are logged in

Need to search on GitHub? Make an account! Don’t want to make an account? Leave!

syndackson 46% of Americans didn't read a book in 2023

You obviously don’t read good novels.

syndackson Ask HN: Career for someone good at making time-sensitive critical decisions?

Designated hitter in the MLB

syndackson 'Stupid,' 'shameful:' Tech workers on Y Combinator CEO Garry Tan's rant

He was only quoting Tupac…

syndackson MFA today is both 'simple' and non-trivial work

I would respectfully disagree. For my Masters in Fine Arts (Creative Writing), I had to write a novel in the style of a dystopic post-modernist. And this was before ChatGPT.