Alignment Is Proven To Be Solvable

ADD / XOR / ROL: A non-anthropomorphized view of LLMs

In many discussions where questions of "alignment" or "AI safety" crop up, I am baffled by seriously intelligent people imbuing almost magic...

Understanding Understanding: A Pragmatic Framework Motivated by...

Motivated by the rapid ascent of Large Language Models (LLMs) and debates about the extent to which they possess human-level qualities, we propose a framework for testing whether any agent (be it...

Epistemological Fault Lines Between Human and Artificial Intelligence

Large language models (LLMs) are widely described as artificial intelligence, yet their epistemic profile diverges sharply from human cognition. Here we show that the apparent alignment between...

LLMs and World Models, Part 1

How do Large Language Models Make Sense of Their “Worlds”?

Artificial intelligences and human scientists exhibit...

We investigate the effectiveness of artificial intelligences (AI)-specifically large language models (LLMs)-relative to human scientists at high-level cognitive tasks in social science such as...

Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via...

Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes. While such adaptation is generally...

There's Something Fundamentally Wrong With LLMs

LLMs aren't trained on the "vast majority of speech," experts warn, a major blind spot that could have sweeping consequences.

Large language model

A large language model (LLM) is a neural network trained on a vast amount of text for natural language processing tasks, especially language generation. LLMs can typically generate, summarize, translate, and analyze text in many contexts, and are a foundational technology behind modern chatbots.[1] Biased or inaccurate training data can make an LLM's output less reliable.[2]

Illusions of Understanding from Outsourcing Thinking to LLMs

Some illusions of understanding are an inevitable part of the research process, while others can be avoided or overcome by careful critical thinking and observation. We are facing an increased risk of avoidable illusions as more research activities are delegated to large language models (LMM). LLMs can be useful but they cannot think, and their use can undermine our thinking and understanding. Thinking for ourselves is hard and error prone but worthwhile - and there are no shortcuts to understanding.

Understanding Reasoning LLMs

Methods and Strategies for Building and Refining Reasoning Models

AI Large Language Model Training: The Potential Risks of Ideological Skewing — PSG Consulting

LLMs (AI Large Language Models) have become part of everyday life. Systems such as ChatGPT, Claude, Gemini, Meta AI (Llama) and X.ai's Grok handle billions of interactions daily. They increasingly shape what information people encounter and in what order, subtly deciding what's important and even what is true, sometimes without users realizing it. Because LLMs wield growing power over information exposure, it is vital to recognize the political and ideological structures at multiple stages of their design, and to identify manipulation risks. 

Why Are LLMs Smart?

A popular way to explain how current LLMs work is to say that “all” they do is predict the next most likely word in a sentence.

Hypothesis generation and updating in large language models

Large language models (LLMs) increasingly help people solve problems, from debugging code to repairing machinery. This process requires generating plausible hypotheses from partial descriptions,...

Solving a Million-Step LLM Task with Zero Errors

LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans,...

LLMs and people both learn to form conventions -- just not with each other

Humans align to one another in conversation -- adopting shared conventions that ease communication. We test whether LLMs form the same kinds of conventions in a multimodal communication game. Both humans and LLMs display evidence of convention-formation (increasing the accuracy and consistency of their turns while decreasing their length) when communicating in same-type dyads (humans with humans, AI with AI). However, heterogenous human-AI pairs fail -- suggesting differences in communicative tendencies. In Experiment 2, we ask whether LLMs can be induced to behave more like human conversants, by prompting them to produce superficially humanlike behavior. While the length of their messages matches that of human pairs, accuracy and lexical overlap in human-LLM pairs continues to lag behind that of both human-human and AI-AI pairs. These results suggest that conversational alignment requires more than just the ability to mimic previous interactions, but also shared interpretative biases toward the meanings that are conveyed.