Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 59 min 33 sec ago

Ask HN: Why is my Claude experience so bad? What am I doing wrong?

Fri, 02/13/2026 - 3:09am

I stopped my CC Max plan a few months ago, but I'm trying it again for fun after seeing their $30 billion series G or whatever.

It just doesn't work. I'm trying to build a simple tool that will let me visualize grid layouts.

It needs to toggle between landscape/portrait, and implement some design strategies so I can see different visualizations of the grid. I asked it to give me a slider to simulate the number of grids.

1st pass, it made something, but it was squished. And toggling between landscape and portrait made it so it squished itself the other way so I couldn't even see anything.

2nd pass, syntax error.

3rd try I ask it to redo everything from scratch. It now has a working slider, but the landscape/portrait is still broken.

4th try, it manages to fix the landscape/portrait issue, but now the issue is that the controls are behind the display so I have to reload the page.

5th try, it manages to fix this issue, but now it is squished again.

6th try, I ask it to try again from scratch. This time it gives me a syntax error.

This is so frustrating.

Comments URL: https://news.ycombinator.com/item?id=47000206

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: I built a simple quant scanner for mean-reversion setups (ZcoreAI)

Fri, 02/13/2026 - 3:04am

Hi HN — I built a small web app that scans a list of tickers across multiple timeframes and flags potential overbought/oversold mean‑reversion setups using a regression-channel Z‑score.

Live MVP: https://zcoreai.onrender.com/

What it does:

Pick tickers + timeframes, then run a scan

Outputs a matrix of signals (simple labels now; “expert” view shows exact values of Z-Score)

Why: I wanted something fast to answer “what’s oversold / overbought right now?” without opening all charts on every timeframes on TradingView.

Notes / current state:

- Early MVP, UI is intentionally minimal

I’d love feedback on:

- Whether the output is understandable/useful

- Which features you’d want next (alerts, presets, exports, etc.)

- Any obvious UX issues or missing pieces for a tool like this

Happy to answer questions and share implementation details if people are interested.

Comments URL: https://news.ycombinator.com/item?id=47000182

Points: 1

# Comments: 1

Categories: Hacker News

Invisible Prompt Injection

Fri, 02/13/2026 - 3:03am
Categories: Hacker News

A simple way to track howcooked you are, daily

Fri, 02/13/2026 - 3:03am

Article URL: https://howcooked.me/

Comments URL: https://news.ycombinator.com/item?id=47000170

Points: 1

# Comments: 0

Categories: Hacker News

CSS-Doodle

Fri, 02/13/2026 - 3:02am

Article URL: https://css-doodle.com/

Comments URL: https://news.ycombinator.com/item?id=47000164

Points: 2

# Comments: 0

Categories: Hacker News

Small Language Models (SLMs) vs. Large Language Models (LLMs)

Fri, 02/13/2026 - 2:59am

Abstract

The last five years have seen explosive progress in large language models (LLMs) — exemplified by systems such as ChatGPT and GPT-4 — which deliver broad capabilities but at heavy computational, latency, privacy, and cost budgets. In parallel, a renewed research and engineering focus on Small Language Models (SLMs) — compact, task-optimized models that run on-device or on constrained servers — has produced techniques and models that close much of the gap while enabling new applications (on-device inference, embedded robotics, low-cost production). This article/review compares SLMs and LLMs across design, training, deployment, and application dimensions; surveys core compression methods (distillation, quantization, parameter-efficient tuning); examines benchmarks and representative SLMs (e.g., TinyLlama); and proposes evaluation criteria and recommended research directions for widely deployable language intelligence. Key claims are supported by recent surveys, empirical papers, and benchmark studies.

1. Introduction & Motivation

Large models (billions to hundreds of billions of parameters) have pushed capabilities for zero-shot reasoning, instruction following, and multi-turn dialogue. However, their deployment often requires large GPUs/TPUs, reliable cloud connectivity, and high inference cost — constraints that hinder low-latency, private, and offline applications (mobile apps, robots, IoT). Small Language Models (SLMs) are intentionally compact architectures (ranging from ~100M to a few billion parameters) or compressed variants of LLMs designed for on-device or constrained-server inference. SLMs are not merely “smaller copies” of LLMs: the field now includes architecture choices, fine-tuning regimes, and tooling (quantization, distillation, pruning) that produce models tailored for specific constraints and use-cases. Recent comprehensive surveys document this growing ecosystem and its practical impact.

2. Definitions & Taxonomy

LLM (Large Language Model): Very large transformer-based models (≥10B params typical) trained on massive corpora. Strengths: generality, emergent capabilities. Weaknesses: cost, latency, privacy exposure.

SLM (Small Language Model): Compact models (≈10⁷–10⁹+ params) or aggressively compressed LLM variants that aim for high compute/latency efficiency while retaining acceptable task performance. SLMs include purpose-built small architectures (TinyLlama), distilled students (DistilBERT style), and heavily quantized LLMs.

Compression & Efficiency Methods: Knowledge distillation, post-training quantization (GPTQ/AWQ/GGUF workflows), pruning, low-rank/adapters (LoRA), and mixed-precision training.

Comments URL: https://news.ycombinator.com/item?id=47000145

Points: 1

# Comments: 0

Categories: Hacker News

OfCom fines 4chan £520k

Fri, 02/13/2026 - 2:57am
Categories: Hacker News

A Meditation on AI Identity

Fri, 02/13/2026 - 2:55am

Article URL: https://soul.md/

Comments URL: https://news.ycombinator.com/item?id=47000111

Points: 1

# Comments: 1

Categories: Hacker News

Ask HN: Where to find people to discuss the future of AI?

Fri, 02/13/2026 - 2:19am

I am building an AI product. And am in constant anxiety that I am missing on ideas.

I have moments where I want to desperately discuss what I am thinking but have no friend that would like to participate in that?

What should I do about it?

Most people consider AI as some tool that they can chat with. But I want to discuss stuff such as the "self evolving software" vs "An AI app builder" and so on...

Comments URL: https://news.ycombinator.com/item?id=46999872

Points: 1

# Comments: 0

Categories: Hacker News

Pages