Hacker News: 44za12

New comment by 44za12 in "Ask HN: Who wants to be hired? (July 2026)"

44za12 — Wed, 01 Jul 2026 19:15:39 +0000

Location: UAE Remote: Preferred Want to relocate: No

Philosophy: Brutally Efficient

More: https://aazar.me

Stop generating what you already have

44za12 — Fri, 26 Jun 2026 10:30:06 +0000

Article URL: https://aazar.me/posts/stop-generating-what-you-already-have

Comments URL: https://news.ycombinator.com/item?id=48684892

Points: 2

# Comments: 0

Horcrux – Distributed, Zero-Trust Secret Manager

44za12 — Sun, 21 Jun 2026 09:06:25 +0000

Article URL: https://github.com/44za12/horcrux

Comments URL: https://news.ycombinator.com/item?id=48617038

Points: 3

# Comments: 2

Lattice Deduction Transformers

44za12 — Tue, 02 Jun 2026 09:17:31 +0000

Article URL: https://arxiv.org/abs/2605.08605

Comments URL: https://news.ycombinator.com/item?id=48367804

Points: 4

# Comments: 0

MiniMax M3

44za12 — Mon, 01 Jun 2026 07:30:49 +0000

Article URL: https://xcancel.com/MiniMax_AI/status/2061266317815296322

Comments URL: https://news.ycombinator.com/item?id=48353665

Points: 5

# Comments: 0

δ-mem: Efficient Online Memory for Large Language Models

44za12 — Sat, 16 May 2026 09:30:06 +0000

Article URL: https://arxiv.org/abs/2605.12357

Comments URL: https://news.ycombinator.com/item?id=48158506

Points: 240

# Comments: 60

Beyond Semantic Similarity

44za12 — Tue, 12 May 2026 19:51:41 +0000

Article URL: https://arxiv.org/abs/2605.05242

Comments URL: https://news.ycombinator.com/item?id=48113518

Points: 68

# Comments: 15

New comment by 44za12 in "I run multiple $10K MRR companies on a $20/month tech stack"

44za12 — Sun, 12 Apr 2026 08:18:30 +0000

I read it as an article in defence of boring tech with a fancier/clickbaity title.

Here’s the more honest one i wrote a while back:

https://aazar.me/posts/in-defense-of-boring-technology

New comment by 44za12 in "Qwen3.5 Fine-Tuning Guide"

44za12 — Wed, 04 Mar 2026 16:47:24 +0000

Specialised models easily beat SOTA, case in point: https://nehmeailabs.com/flashcheck

New comment by 44za12 in "Number Research Inc"

44za12 — Wed, 04 Mar 2026 05:14:34 +0000

All of us use the same keyboards more or less, maybe us randomly typing a large number is not as random as we would like to think. Just like how “asdf”, “xcyb” are common strings because these keys are together, there has to be some pattern here as well.

In Defense of Boring Technology

44za12 — Tue, 17 Feb 2026 06:43:27 +0000

Article URL: https://aazar.me/posts/in-defense-of-boring-technology

Comments URL: https://news.ycombinator.com/item?id=47044412

Points: 1

# Comments: 0

Show HN: RightSize CLI, Find the cheapest LLM that works for your prompt

44za12 — Wed, 28 Jan 2026 10:50:41 +0000

RightSize runs your prompt against candidate models (Kimi, GLM, Qwen, Gemma etc.) in parallel via OpenRouter. Then it uses a stronger model as a Judge to score accuracy against a baseline model.

Happy to answer questions.

Comments URL: https://news.ycombinator.com/item?id=46793694

Points: 3

# Comments: 0

New comment by 44za12 in "Tell HN: I cut Claude API costs from $70/month to pennies"

44za12 — Mon, 26 Jan 2026 13:24:03 +0000

Yes, I included a 'Model Selection Cheat Sheet' in the README (scroll down a bit).

I map them by task type:

Tiny (<3B): Gemma 3 1B (could try 4B as well), Phi-4-mini (Good for classification). Small (8B-17B): Qwen 3 8B, Llama 4 Scout (Good for RAG/Extraction). Frontier: GPT-5, Llama 4 Maverick, GLM, Kimi

Is that what you meant?

Show HN: LLM Sanity Checks – A practical guide to not over-engineering AI

44za12 — Mon, 26 Jan 2026 12:49:12 +0000

I keep seeing teams use frontier models for tasks a regex or a 4B model could do cheaper and faster.

This repo is a collection of opinionated patterns and heuristics to help you rethink the architecture of your AI workflows and ease the decision-making process while ensuring maximum efficiency.

It covers:

- A decision tree for architectural sanity checks. - Tradeoffs between JSON and delimiter-separated output. - Patterns for cascading models (verifying small models before calling big ones).

Open to feedback on other anti-patterns you've seen in production.

Comments URL: https://news.ycombinator.com/item?id=46765011

Points: 1

# Comments: 0