44za12

11 日前議論

Location: UAE Remote: Preferred Want to relocate: No

Philosophy: Brutally Efficient

More: https://aazar.me

3 か月前議論

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

44za12

4 か月前議論

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

44za12

4 か月前議論

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.

44za12

6 か月前議論

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?

44za12

6 か月前議論

This is the way. I actually mapped out the decision tree for this exact process and more here:

https://github.com/NehmeAILabs/llm-sanity-checks

44za12

6 か月前議論

For simple extraction tasks, a delimiter-separated string uses 11 tokens vs 35 for JSON. Output tokens are the latency bottleneck.

投稿

Stop generating what you already have

Horcrux – Distributed, Zero-Trust Secret Manager

Lattice Deduction Transformers

MiniMax M3

δ-mem: Efficient Online Memory for Large Language Models

Beyond Semantic Similarity

In Defense of Boring Technology

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

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

Stop using JSON for LLM structured output

FlashCheck-270M: Open weights for fact verification (Apache 2.0, WASM Demo)

コメント