Topic: llms

48 stories found

Yesterday

trending62

LLMs as a Cognitive Virus

The article discusses how large language models (LLMs) can spread rapidly and influence human thought processes, likening their impact to that of a cognitive virus. This comparison highlights the potential for LLMs to significantly shape public opinion and individual beliefs on a wide scale, underscoring the need for awareness about their influence.

arxiv.org↗

Friday, September 4, 2026

trending52

Show HN: TERMy – A fast terminal assistant that does not use LLMs

TERMy is a new terminal assistant tool designed to enhance productivity without relying on large language models, offering faster and more direct command assistance. Its significance lies in providing an alternative for users seeking efficient terminal interactions free from the potential biases and limitations associated with LLMs.

github.com↗
research40

Where Does Harness-Optimization Value Live? Localized Gains and the Budget-Splitting Trap in Self-Evolving LLM Agents

The article explores how optimizing the "harness" or context around large language models can enhance their performance as autonomous agents. It highlights that while such optimizations can yield localized improvements, they may not always translate to overall budget efficiency, cautioning against over-reliance on budget-splitting strategies for self-evolving LLMs.

arxiv.org↗

Saturday, August 29, 2026

48 of 48 items shown. Sources: 107 days indexed.