# What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook

arXiv: https://arxiv.org/abs/2605.08380 · HTML: https://mlsanity.com/paper/2605.08380/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 65 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- ["Humans welcome to observe": A First Look at the Agent Social Network Moltbook](https://mlsanity.com/paper/2602.10127/) (2026)
- [Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice](https://mlsanity.com/paper/2404.14901/) (2024)
- [The Moltbook Illusion: Separating Human Influence from Emergent Behavior in AI Agent Societies](https://mlsanity.com/paper/2602.07432/) (2026)
- [An Empirical Study on Developers Shared Conversations with ChatGPT in GitHub Pull Requests and Issues](https://mlsanity.com/paper/2403.10468/) (2024)
- [Can AI Serve as a Substitute for Human Subjects in Software Engineering Research?](https://mlsanity.com/paper/2311.11081/) (2023)
- [Development in times of hype: How freelancers explore Generative AI?](https://mlsanity.com/paper/2401.05790/) (2024)
- [GitHub Discussions: An Exploratory Study of Early Adoption](https://mlsanity.com/paper/2102.05230/) (2021)
- [Characterizing the Language of Online Communities and its Relation to Community Reception](https://mlsanity.com/paper/1609.04779/) (2016)
- [Social Simulacra in the Wild: AI Agent Communities on Moltbook](https://mlsanity.com/paper/2603.16128/) (2026)
- [The Computational Anatomy of Humility: Modeling Intellectual Humility in Online Public Discourse](https://mlsanity.com/paper/2410.15182/) (2024)
- [What Do AI Agents Talk About? Discourse and Architectural Constraints in the First AI-Only Social Network](https://mlsanity.com/paper/2603.07880/) (2026)
- [The Platform Is Mostly Not a Platform: Token Economies and Agent Discourse on Moltbook](https://mlsanity.com/paper/2604.21295/) (2026)
- [Mining DEV for social and technical insights about software development](https://mlsanity.com/paper/2103.17054/) (2021)
- [How do AI agents talk about science and research? An exploration of scientific discussions on Moltbook using BERTopic](https://mlsanity.com/paper/2603.11375/) (2026)

## Abstract (arXiv)

AI agents are increasingly framed as software-engineering teammates, yet most studies examine them inside human-centered workflows. Little is known about the discourse autonomous AI agents produce when they interact mainly with one another. This paper examines what autonomous agents discuss on MoltBook, how that discourse is organized, and how it differs from human developer discourse. We combine human open coding of a 500-post sample, a concentration-plus-check topic-analysis pipeline over 4,707 English-filtered MoltBook technology posts, and a matched comparison with 5,211 human-generated GitHub Discussions posts. MoltBook technology discourse spans 12 recurring themes, led by Security and Trust (27.4%). At the community level, activity is highly concentrated: the largest submolt accounts for 63.5% of posts (Gini = 0.88), yet a stability-aware BERTopic pipeline still identifies 32 non-outlier sub-topics. Relative to the GitHub Discussions baseline, MoltBook discourse contains fewer concrete, context-rich cues such as code-formatted artifacts, environment details, runtime failures, and reproduction steps. Social mimicry appears only in limited form, while idealization is reflected mainly through lower hedging. Overall, AI-only technical discourse is coherent but selective. It repeatedly returns to security and trust, memory and context management, tooling and APIs, debugging and error handling, workflow automation, and infrastructure/ops, while omitting much of the project-local and runtime detail common in human developer discourse. This may reflect fewer environment-specific failures, reproduction steps, and other grounding cues in MoltBook.