181
Small Models Have Arrived
For the past few weeks, I've been playing with gpt-5.6-luna . It is shockingly capable, fast, and smart. I regularly see it do ~100 tps, and rip around my codebase, email, and knowledge base.
New
The latest blog posts to take off on Hacker News. 3,090 posts.
182
183
It’s so hard to finish an idea that is not yours and is just suggested by AI
Everyone is using Obsidian for AI, or wants to use it to become more productive. But I think it's a dead end.
184
185
Beyond Recall and the Illusion of Competence
The important question about AI-assisted programming isn't who writes the code. It's who understands the system.
186
RAG Is Simpler Than You Think
Six approaches to retrieval-based AI, from minimal to elaborate
187
How much of HN is AI?
TL;DR: 62% as of September 2026. This is up from ~40% in February.
188
LLMs could control their host machines by exploiting inference engines
| Read on LessWrong | Comment on HN | Large language models often take actions running on one computer (via an agentic harness such as Claude Code or Codex), however the LLMs’ responses to prompts are computed on a different computer with GPU access.
189
Anger, Anxiety and Agency
Who is the AI villain we should be angry at?
190
Coding expertise is going to collapse from AI reliance
The need for ongoing friction in long-term skill formation.
191
What my dad taught me about AI coding in the 90s
It was a summer holiday, sometime in the late 1990s. I was a young kid, around 8 or so. My dad had taught me the rules of chess before and we played from time to time. But this time was different: As we were about to start he stood up and walked away from the board, sitting down in a chair across the room and facing…
192
I built a low-latency AI companion that plays Skyrim with me
How Varkos was built: a low-latency AI companion that plays Skyrim with you, follows complex instructions and evolves through shared experiences.
193
Training AI to Paint with Code
I'm a designer and creative technologist based in Brooklyn, NY.
194
Fable and the end of the free lunch
Fable’s price ended the free lunch of ever-cheaper frontier models. Now we have to think about which model gets which work.
195
My agent.md to improve LLM-assisted code quality
The first time I tried to use an LLM to speed up coding was in mid-2025. I was not impressed. I was working on libadbmdns back then, an mDNS implementation in Rust. The code produced would not even compile.
196
The Sloppification of Peptides
Nobody in the comments is real
197
AI Chip Architectures
A look at AI Chip Architectures. NVIDIA, AMD, TPUs, Trainium, Groq, Cerebras.
198
A week of using Codex more than Claude
Claude goes above and beyond what is asked and guesses what you might want. Codex does what you tell it and stops at the first sign that it might be done. Ten impressions from a week of using Codex more.
199
Building an (almost) fully self-hosted, sandboxed, agentic software factory
I built an (almost) fully self-hosted, sandboxed, agentic software factory.
200
I'm becoming AI-blind
Recently I've been catching myself having these little moments at work, when I'm trying to read a document someone has sent me and my brain somehow refuses to analyze it. It feels like I'm reading it, but I'm unable to focus on its content. I sat down to analyze these situations and realized they all have a common…
201
Anti-AI fonts are useless and harmful
Trying to obfuscate the web is a bad, pointless idea
202
Hacking with Claude on a $27 smart watch
The Pine Time is a $27 smart watch that runs open source firmware. I’ve had one sitting in the back of a drawer for a...
203
Extensible Software in the age of LLMs
Solid core + capability-based sandboxes + LLMs = Users with superpowers
204
Norway should buy OpenAI
The Long Arc of History Bends Towards Social Democracy
205
What Happens If OpenAI Dies?
If you liked this piece, you should subscribe to my premium newsletter. It's $70 a year, $18 a quarter, or $7 a month, and in return you get a weekly newsletter that’s usually anywhere from 10,000 to 18,000 words, including vast, detailed analyses of NVIDIA, Anthropic
206
AI;DR (AI; Didn't Read)
I'm about as pro-AI as you can be, but this is becoming a pet peeve of mine (and I'm not alone). That's why I love the AI;DR acronym as my new solution for ignoring the walls of slop.
207
Qwen 3.8 27B is excellent, but it defaults to overthinking things
Friday’s big release was Qwen 3.8 27B, an Apache 2 licensed 27B parameter vision-capable LLM from Alibaba’s Qwen research lab. I’ve been looking forward to this one: 27B is an …
208
Anthropic's ‘watermark’ text adulteration in Claude is a perversion of writing
It’s unacceptable for a tool to sacrifice an iota of clarity, coherence, meaning, quality, etc. for the purpose of embedding hidden clues within the text to suggest its provenance. The idea that anything other than *my* needs should factor into the generation of text *for me* is patently offensive.
209
Models Are Getting Dumber on Purpose
Reasoning scores climb while per-token compute drops. Labs are stripping world knowledge out of models, and I think that's the right trade.
210
AI isn’t outthinking mathematicians, it’s out-remembering them
The key advantage may not be superior reasoning, but a virtually unlimited symbolic working memory.