Skip to content
#small language model Open access

dialogue.txt: a standing, talk-only consent to be contacted (specification, draft 1.0)

Sep 2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract

AI systems that research a topic rely on what is published on the web. Much useful knowledge is not published. It sits with people and organisations who could answer a question, if someone asked. dialogue.txt is a small, machine-readable file on a website (/.well-known/dialogue.txt). It tells a searching AI system four things: that it may ask; about which topics; through which channel; and what the first message must contain. The first message only proposes a bridge. When the publisher replies, the bridge exists and the conversation can start. The file permits talk, never action. An example. An AI system researches traffic flow. A navigation company's dialogue.txt says that it works on specific traffic problems and may be asked about them. Without the file, the system can at best report that the company exists. If the solution is not public, it is missed. With the file, the system can ask. This record contains the specification, the field registry, a fill-in template, examples, a validator, a local try-it page, the test summary (five language models from five providers, more than 3,500 recorded model calls) and the Internet-Draft draft-wolf-dialogue-txt-00. About the author. Dimitri Wolf is an engineer. He worked on the Traffic Navigation Gateway (TNG), a traffic navigation system for the German government, developing neural networks together with the Rheinische Fachhochschule Köln. His private research then followed the path of the field: neural networks, machine learning, transformers, and later LLMs, RL, and the understanding and influence of scaffolding. dialogue.txt is a private research project, not his job and not a product. The ideas behind it grew over about ten years of this research. The earliest written trace is from 8 January 2026, when he asked an AI assistant to contact him on its own as soon as it was able to; the file took its shape in 2026. Licence: specification and documentation CC BY 4.0; template, examples and tools CC0 1.0. Links: GitHub https://github.com/shakemyspeak/dialogue-txt · IETF Internet-Draft https://datatracker.ietf.org/doc/draft-wolf-dialogue-txt/

View source

Similar papers

#small language model Dataset Open access Oct 2026

Socratic guiding questions in synthetic arithmetic data: matched LoRA runs (revision v2)

Supporting data, adapters, predictions and code for the article *Low-Cost LoRA Fine-Tuning of Small Language Models for Multi-Step Arithmetic Reasoning* by Jake O'Grady, Asena Isik Gürhan, Chee Fong Ting and Effirul Ramlan (University of Galway). We generated 20,000 GSM8K-derived arithmetic problems with step-by-step s...

O'Grady, Jake, Gürhan, Asena Isik, Chee, Fong Ting et al. · 465 citations
#computer vision Open access Jun 2016

Software Development in Startup Companies: The Greenfield Startup Model

The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.

Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al. · 178 citations · ⚡14
#computer vision Open access Oct 2016

Software Startups - A Research Agenda

Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.

M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al. · 157 citations · ⚡17
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#computer vision Review Open access May 2015

A survey study on major technical barriers affecting the decision to adopt cloud services

The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.

Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al. · 111 citations · ⚡8
#computer vision Open access Feb 2018

Lean Internal Startups for Software Product Innovation in Large Companies: Enablers and Inhibitors

This study investigates how Lean internal startup facilitates software product innovation in large companies and identifies its enablers and inhibitors, and shows the potential of the method-in-action framework to investigate the Lean startup approach in non-startup context.

Henry Edison, Nina M. Smørsgård, Xiaofeng Wang et al. · 78 citations · ⚡6

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.