· ai
Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models
Read more about Language Agent Tree Search Unifies Reasoning, Acti...
-
- · ai
On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs
Article URL: https://arxiv.org/abs/2512.01797 Comments URL: https://news.ycombinator.com/item?id=46354773 Points: 25 Comments: 38...
- · ai
How Transformers Really Think: Inside the Brain of an AI Language Model
Introduction Most people think AI models are mysterious black boxes, but they’re overthinking it. When you type a sentence into a model, it doesn’t see words—i...
- · ai
LLM Year in Review
19 Dec, 2025 !unnamedhttps://bear-images.sfo2.cdn.digitaloceanspaces.com/karpathy/unnamed.webp 2025 has been a strong and eventful year of progress in LLMs. The...
- · ai
History LLMs: Models trained exclusively on pre-1913 texts
Article URL: https://github.com/DGoettlich/history-llms Comments URL: https://news.ycombinator.com/item?id=46319826 Points: 327 Comments: 113...
- · it
Feeding the machine
When he was 19 years old, Brendan Foody started Mercor with two of his high school friends as a way for his other friends, who also had startups, to hire softwa...
- · ai
Trinity AGA Architecture: Technical Deep Dive into a Governance First AI System
Introduction In the first article I introduced Trinity AGA Architecture as a constitutional framework for reflective AI. This follow‑up dives into the technica...
- · ai
BIG STEPS TO TRANSFORMER (PART 2): BUILDING THE TRANSFORMER
The Naive Approach Let’s be specific: for each timestep we want to see every character behind us in order to make our decision. A simple way is to carry the da...
- · ai
LLM is not Gen AI.
!Cover image for LLM is not Gen AI.https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3....
- · ai
[Paper] BERnaT: Basque Encoders for Representing Natural Textual Diversity
Language models depend on massive text corpora that are often filtered for quality, a process that can unintentionally exclude non-standard linguistic varieties...
- · ai
New training method boosts AI multimodal reasoning with smaller, smarter datasets
Researchers at MiroMind AI and several Chinese universities have released OpenMMReasoner, a new training framework that improves the capabilities of language mo...
- · ai
Syntax hacking: Researchers discover sentence structure can bypass AI safety rules
New research offers clues about why some prompt injection attacks may succeed....