· ai
What Really Happens When an LLM Chooses the Next Token🤯
LLM outputs sometimes feel stable. Sometimes they suddenly become random. Often, the only thing that changed is a parameter. So what actually happens at the mom...
-
- · ai
LLM poetry and the 'greatness' question: Experiments by Gwern and Mercor
Article URL: https://hollisrobbinsanecdotal.substack.com/p/llm-poetry-and-the-greatness-question Comments URL: https://news.ycombinator.com/item?id=46575268 Poi...
- · ai
Task-free intelligence testing of LLMs
Article URL: https://www.marble.onl/posts/tapping/index.html Comments URL: https://news.ycombinator.com/item?id=46545587 Points: 11 Comments: 1...
- · ai
Understanding DLCM: A Deep Dive into Its Core Architecture and the Power of Causal Encoding
Modern Language Models and the Dynamic Latent Concept Model DLCM Modern language models have evolved beyond simple token‑by‑token processing, and the Dynamic L...
- · ai
AI Models Are Starting to Learn by Asking Themselves Questions
An AI model that learns without human input—by posing interesting queries for itself—might point the way to superintelligence....
- · ai
I broke GPT-2: How I proved Semantic Collapse using Geometry (The Ainex Limit)
TL;DR I forced GPT‑2 to learn from its own output for 20 generations. By Generation 20 the model lost 66 % of its semantic volume and began hallucinating state...
- · ai
What I Learned Trying (and Mostly Failing) to Understand Attention Heads
What I initially believed Before digging in, I implicitly believed a few things: - If an attention head consistently attends to a specific token, that token is...
- · ai
The US Invaded Venezuela and Captured Nicolás Maduro. ChatGPT Disagrees
Some AI chatbots have a surprisingly good handle on breaking news. Others decidedly don't....
- · ai
Recursive Language Models
Article URL: https://arxiv.org/abs/2512.24601 Comments URL: https://news.ycombinator.com/item?id=46475395 Points: 8 Comments: 0...
- · ai
Instructions Are Not Control
!Cover image for Instructions Are Not Controlhttps://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-u...
- · ai
I Asked for a Parrot. The AI Gave Me a Crow and Set It Free.
I asked an AI model to generate a parrot. It confidently generated a crow. And then—metaphorically—set it free. > “Maine bola tota bana, isne kavva bana ke uda...
- · ai
Part 2: Why Transformers Still Forget
Part 2 – Why Long‑Context Language Models Still Struggle with Memory second of a three‑part series In Part 1https://forem.com/harvesh_kumar/part-1-long-context-...