Digitalia #838 - Agentic coding e beni culturali
· 1 h 05 min · Episode 838
Episode Digitalia #838 - Agentic coding e beni culturali
Modelli di linguaggio di grandi dimensioni e programmazione agentica nel mondo dei beni culturali. AI generativa, ontologie e archeologia aumentata: come si insegna a una macchina a capire la cultura.
Dallo studio distribuito di digitalia:Franco Solerio, Francesco Facconi, John Doe
Produttori esecutivi:
Sponsor:Squarespace.com - utilizzate il codice coupon "DIGITALIA" per avere il 10% di sconto sul costo del primo acquisto.
Links:
• On the Dangers of Stochastic Parrots — Bender, Gebru, McMillan-Major, Mitchell (2021) • Stochastic Parrots — voce Wikipedia • Retrieval-Augmented Generation (RAG) — voce Wikipedia • Cos'è il RAG — spiegazione AWS • SPARQL Query Language for RDF — specifica W3C • SPARQL — voce Wikipedia • Knowledge Graphs Generation from Cultural Heritage Texts — paper arXiv (metodologia ATR4CH) • Knowledge Graphs vs. Large Language Models: Competitors or Partners in Supporting Virtual Museums — ACM JOCCH • Knowledge Graphs for Cultural Heritage and Digital Humanities — Proceedings ACM • DocStoLab — Università degli Studi di Salerno • LangGraph — pagina ufficiale LangChain • LangGraph — repository GitHub • Google Agent Development Kit (ADK) — documentazione ufficiale • ADK — annuncio Google Developers Blog • n8n — piattaforma di workflow automation con AI • Introducing the Model Context Protocol — annuncio Anthropic • MCP — specifica ufficiale • Model Context Protocol — voce Wikipedia • Introducing gpt-oss — annuncio OpenAI • gpt-oss-120b — model card su Hugging Face • gpt-oss — repository GitHub • Claude Code — pagina ufficiale Anthropic • Claude Code — repository GitHub • Vibe Coding — voce Wikipedia • Spec-Driven Development with AI — GitHub Blog • How to write a good spec for AI agents — Addy Osmani • AI Agent Orchestration Patterns — Microsoft Azure Architecture Center • LangGraph Multi-Agent Workflows — blog LangChain
Gingilli del giorno:
Supporta Digitalia, diventa produttore esecutivo.
Links in the notes 20
- https://mastodon.social/@francosolerio
- https://livellosegreto.it/@mdsol
- https://faculty.washington.edu/ebender/papers/Bender-NE-ExpAI.pdf?utm_source=digitaliafm&utm_medium=podcast
- https://en.wikipedia.org/wiki/Stochastic_parrot?utm_source=digitaliafm&utm_medium=podcast
- https://en.wikipedia.org/wiki/Retrieval-augmented_generation?utm_source=digitaliafm&utm_medium=podcast
- https://aws.amazon.com/what-is/retrieval-augmented-generation/?utm_source=digitaliafm&utm_medium=podcast
- https://www.w3.org/TR/rdf-sparql-query/?utm_source=digitaliafm&utm_medium=podcast
- https://en.wikipedia.org/wiki/SPARQL?utm_source=digitaliafm&utm_medium=podcast
- https://arxiv.org/abs/2511.10354?utm_source=digitaliafm&utm_medium=podcast
- https://dl.acm.org/doi/10.1145/3756016?utm_source=digitaliafm&utm_medium=podcast
- https://dl.acm.org/doi/abs/10.1145/3607542.3617354?utm_source=digitaliafm&utm_medium=podcast
- https://sites.google.com/unisa.it/docstolab/home?utm_source=digitaliafm&utm_medium=podcast
- https://www.langchain.com/langgraph?utm_source=digitaliafm&utm_medium=podcast
- https://github.com/langchain-ai/langgraph?utm_source=digitaliafm&utm_medium=podcast
- https://google.github.io/adk-docs/?utm_source=digitaliafm&utm_medium=podcast
- https://developers.googleblog.com/en/agent-development-kit-easy-to-build-multi-agent-applications/?utm_source=digitaliafm&utm_medium=podcast
- https://n8n.io/?utm_source=digitaliafm&utm_medium=podcast
- https://www.anthropic.com/news/model-context-protocol?utm_source=digitaliafm&utm_medium=podcast
- https://modelcontextprotocol.io/specification/2025-11-25?utm_source=digitaliafm&utm_medium=podcast
- https://en.wikipedia.org/wiki/Model_Context_Protocol?utm_source=digitaliafm&utm_medium=podcast
Chapters
Transcript
Shows are listed from Apple Podcasts' charts and directory, and Podcast Index where it is used. Every show and episode belongs to its publisher and plays from the publisher's own feed; this site hosts none of them. Explicit shows are for adult profiles only, and children’s profiles hear only children’s shows. More about this list.