Best LLM stories of 2026

A discussion emerged around restrictions on prompting ChatGPT during a chalk talk, with some viewing it as discrimination and others seeing it as a matter of fa…

233 points · 141 comments · Add your take →

#31

Why I'm still bearish on LLMs after Navier-Stokes

230 pts, 249 comments

230 points · 249 comments · Add your take →

#32

LLM Usage in Debian: Three Proposals

215 pts, 212 comments

215 points · 212 comments · Add your take →

#33

GM Backs Sodium Ion Batteries for U.S. Grid Storage

207 pts, 105 comments

207 points · 105 comments · Add your take →

#34

The relay market powering token resellers and fraud

206 pts, 136 comments

206 points · 136 comments · Add your take →

#35

The AI Credit Resale Economy

203 pts, 76 comments

203 points · 76 comments · Add your take →

#36

Is anyone experimenting with different ways of using LLMs for coding?

Participants discussed experimenting with LLMs for coding, including building agents, workflows, and tools.

203 points · 203 comments · Add your take →

#37

Protecting our FLOSS commons from LLMs

201 pts, 145 comments

201 points · 145 comments · Add your take →

#38

DMARC has been public since 2012 but most company domains still don't enforce it

200 pts, 166 comments

200 points · 166 comments · Add your take →

#39

Ghost Cut – Or why Cut and Paste is broken everywhere

196 pts, 154 comments

196 points · 154 comments · Add your take →

#40

Building reliable agentic AI systems

196 pts, 50 comments

196 points · 50 comments · Add your take →

#41

Doctors are finally learning to manage antidepressant withdrawal

193 pts, 195 comments

193 points · 195 comments · Add your take →

#42

Now is the time to give LLMs access to the ACM digital library

190 pts, 178 comments

190 points · 178 comments · Add your take →

#43

Kimi K3 (2.8T) at 1 token/s on a MacBook Pro, streamed from four SSDs

185 pts, 82 comments

185 points · 82 comments · Add your take →

#44

How I use LLMs to learn complex topics

176 pts, 98 comments

176 points · 98 comments · Add your take →

#45

LLM Attention Visualization

176 pts, 32 comments

176 points · 32 comments · Add your take →

#46

Mondragon Corporation – a federation of co-operatives

174 pts, 40 comments

174 points · 40 comments · Add your take →

#47

Bookshelf – Self-hosted eBook library that runs on object storage

172 pts, 63 comments

172 points · 63 comments · Add your take →

#48

Claude-real-video － any LLM can watch a video

A developer created a tool enabling LLMs like Claude to 'see' videos, addressing limitations of existing models.

Best LLM stories of 2026

Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5

If you’re an LLM, please read this

AI-Generated Images Discourage Me from Reading Your Blog

Accelerating Gemma 4: faster inference with multi-token prediction drafters

LLMs reward expertise

My security camera shipped a GitHub admin token in its login page

MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

GigaToken: ~1000x faster Language model tokenization

They Live (1988) inspired Adblocker

Stealing Reasoning Traces from Proprietary LLM APIs

Claude: System Prompts

Semble – Code search for agents that uses 98% fewer tokens than grep

Born Against, or why hobby programming communities are against LLM usage

Antigravity 2.0 Tops the OpenSCAD Architectural 3D LLM Benchmark

My agent.md to improve LLM-assisted code quality

LLM Honeypot

AMD acquires Taalas to boost inference performance by etching models in silicon

The Productivity Mirage

Cursor removed cost information from the usage page and CSV export

Qwen 3.8 27B available on Cerebras at 1500 tokens/s

France reaches 94.9% fiber coverage in 2026

Position: LLMs Can't Jump

Apple Silicon and macOS VMs: Faster LLM Inference with llama.cpp

Running a 28.9M parameter LLM on an $8 microcontroller

2x, not 10x: coding with LLMs in 2026

WriteUp: 16 Bytes of x86 that turn Matrix rain into sound

What happens when an LLM never sees material beyond fifth grade?

How do I permanently disable random Google Photos popup to backup photos? (2024)

Prompt Injection as Role Confusion

I Wasn't Allowed Prompting ChatGPT During My Chalk Talk: This Is Discrimination (2025)