Hacker News: syndacks

New comment by syndacks in "The bottleneck was never the code"

syndacks — Wed, 06 May 2026 16:45:51 +0000

The archetype of the "jerk engineer" is over, because it turns out coding isn't all that valuable anymore. We now need "engineers" who understand much more than coding.

New comment by syndacks in "Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model"

syndacks — Thu, 23 Apr 2026 02:07:40 +0000

it seemed HN was moving the right direction when we added the "no AI comments", and yet, every single post about a new model is from you and your pelican. it's tired. please stop, it adds no value and has become cliche.

New comment by syndacks in "Ask HN: Are AI mandates a good idea?"

syndacks — Sat, 21 Mar 2026 23:25:57 +0000

I think mandates are irrelevant. Unless you work at a monopoly or cutting edge domain, I don’t see how anything other than a “software factory” wins.

https://openai.com/index/harness-engineering/

New comment by syndacks in "Ask HN: How are people forecasting AI API costs for agent workflows?"

syndacks — Thu, 12 Mar 2026 20:21:37 +0000

lowercasing doesn’t obfuscate the stench of LLM

New comment by syndacks in "Switch to Claude without starting over"

syndacks — Sun, 01 Mar 2026 17:17:14 +0000

I have a 20$ for both and like each for unique reasons. How do you all switch your programming paradigms for Codex vs CC?

New comment by syndacks in "AI Made Writing Code Easier. It Made Being an Engineer Harder"

syndacks — Sun, 01 Mar 2026 15:43:36 +0000

Ai shit post

New comment by syndacks in "Verified Spec-Driven Development (VSDD)"

syndacks — Sun, 01 Mar 2026 03:40:25 +0000

Does anyone have any solid patterns they can share around the “scenarios”/holdouts concept from the Dark Factory, where you create external system(s) to verify your main one?

New comment by syndacks in "A16z partner says that the theory that we’ll vibe code everything is wrong"

syndacks — Fri, 20 Feb 2026 23:55:19 +0000

I largely agree with you. And, given your points about “not going back” — how do you propose interviewing SWEs?

New comment by syndacks in "Child's Play: Tech's new generation and the end of thinking"

syndacks — Fri, 20 Feb 2026 22:54:26 +0000

A lot of people here like this guys writing.

For a longer and more biting critique of SF one should read

Private Citizens (2016) by Tony Tulathimutte

“ Capturing the anxious, self-aware mood of young college grads in the aughts, Private Citizens embraces the contradictions of our new century: call it a loving satire.”

New comment by syndacks in "Gemini 3 Deep Think"

syndacks — Thu, 12 Feb 2026 22:58:38 +0000

The Singularity will occur on a Tuesday, during Chinese New Year

New comment by syndacks in "Ask HN: Who wants to be hired? (February 2026)"

syndacks — Tue, 03 Feb 2026 18:01:17 +0000

  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.

New comment by syndacks in "Kimi K2.5 Technical Report [pdf]"

syndacks — Fri, 30 Jan 2026 23:22:58 +0000

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.

New comment by syndacks in "AI2: Open Coding Agents"

syndacks — Wed, 28 Jan 2026 00:15:37 +0000

LLM shit post

New comment by syndacks in "CLI agents make self-hosting on a home server easier and fun"

syndacks — Sun, 11 Jan 2026 23:40:16 +0000

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”

New comment by syndacks in "Ask HN: What kind of setup do you run for your children?"

syndacks — Tue, 06 Jan 2026 18:19:10 +0000

Crayons, paper, some magnatiles.

New comment by syndacks in "Claude Code On-the-Go"

syndacks — Mon, 05 Jan 2026 00:24:14 +0000

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.

New comment by syndacks in "2025: The Year in LLMs"

syndacks — Thu, 01 Jan 2026 02:56:20 +0000

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?

New comment by syndacks in "Get an AI code review in 10 seconds"

syndacks — Sun, 21 Dec 2025 21:35:53 +0000

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

New comment by syndacks in "New Kindle feature uses AI to answer questions about books"

syndacks — Fri, 12 Dec 2025 21:32:07 +0000

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

New comment by syndacks in "Launch HN: Phind 3 (YC S22) – Every answer is a mini-app"

syndacks — Thu, 04 Dec 2025 02:48:59 +0000

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