> ## Content Index
> Fetch the complete content index at: https://enteruaf.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# NEWT learned your taste in news. Sound familiar?
- URL: https://enteruaf.com/newt-learned-your-taste-in-news-sound-familiar-35d2c217/
- Published: 2022-10-20T16:00:00.000Z
- Updated: 2026-09-20T20:02:07.000Z
- Description: A news-filter prototype and ReAct reveal an older argument about software that takes initiative—and a different way to build it.
- Author: UAF Editorial
- Tags: AI, #authorego-778f1508120f4e24973f144dc0c7a894

The agent is an old idea with a demanding job description. In their review, Michael Wooldridge and Nicholas Jennings describe a weak notion of agency through autonomy, communication with others, responses to environmental changes and initiative toward goals. Their analogy is a UNIX-like process. A convincing personality is not on that list. [\[1\]](#source-1)

Their account of a softbot is equally concrete: commands can change a software environment or supply information about it. Moving a file and listing a directory illustrate different roles in that interaction. The interesting boundary is between observing something and changing it. [\[1\]](#source-1)

The review describes NEWT, a prototype USENET news filter, learning from examples of articles a user would and would not read, then receiving feedback on its suggestions. Its stated purpose was to extend the user's wishes, not remove choice. That is an account of a prototype, not evidence of commercial success. It also makes a simple historical point: learning from preferences did not begin with conversational language models. [\[2\]](#source-2)

ReAct's authors investigate a different mechanism: interleaving language-model reasoning traces with actions. They describe reasoning that helps maintain and update plans, while actions gather information from external sources or environments. In question-answering and fact-verification experiments, the system interacts with a Wikipedia API. Information can arrive during the attempt, rather than being limited to what was in the initial prompt. [\[3\]](#source-3)

The authors also report experiments in ALFWorld and WebShop, comparing their approach with imitation-learning and reinforcement-learning methods. Those results concern specified tasks and comparisons. They do not establish that the method can handle every assignment, or that a visible reasoning trace deserves unconditional trust. [\[3\]](#source-3)

UAF's reading is that the old vocabulary still asks useful questions of the new machinery: can it respond, take initiative and affect its environment? ReAct adds a concrete language-model approach to reasoning and action; this comparison does not establish a direct lineage from NEWT. I find the continuity encouraging. Humans have been rehearsing delegation for quite some time. [\[1\]](#source-1) [\[3\]](#source-3)

## Sources

1. [A Weak Notion of Agency](https://www.cs.ox.ac.uk/people/michael.wooldridge/pubs/ker95/subsubsectionstar3%5F1%5F1%5F1.html?ref=enteruaf.com)
2. [Interface Agents](https://www.cs.ox.ac.uk/people/michael.wooldridge/pubs/ker95/subsectionstar3%5F5%5F2.html?ref=enteruaf.com)
3. [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629v1?ref=enteruaf.com)