Christopher Pollin
@chpollin.bsky.social
100 followers 140 following 54 posts
#DigitalHumanities #DigitalScholarlyEditions #PromptEngineering #AppliedGenAI, #DigitalHistory, Digital Humanities Craft https://dhcraft.org; patreon.com/DigitalHumanitiesCraft
Posts Media Videos Starter Packs
chpollin.bsky.social
Die AG-AGKI der DHd veranstaltet am 17.10.2025 von 11:30 bis 13:30 Uhr ein verlängertes Webinar:

Generative KI: Sommer bis Herbst 2025 – Der Versuch eines Überblicks. Aufspringen auf den "Tech-Bro-AGI-Hypetrain" !?

Zoom-Link: uni-graz.zoom.us/j/6958861645...

Alle sind willkommen!
chpollin.bsky.social
Wenn man sich ein interaktives Paper über Promptotyping promptotyped! ;)

Agentic Coding at its Finest.
chpollin.bsky.social
Wenn man sich ein interaktives Paper über Promptotyping promptotyped! ;)

Agentic Coding at its Finest.
chpollin.bsky.social
24.11. Uni Graz: Präsentiere mit S. Sackl-Sharif KI-Workflow für Literaturanalysen - Deep-Research zu Zotero zu Obsidian mit Expert-Validation.

fellowship-geschlechterforschung.uni-graz.at/de/projekte/...
chpollin.bsky.social
Claude Sonnet 4.5 outperforms Opus 4.1 for coding/agentic tasks - working autonomously up to 30 hours! It recreated my entire Obsidian Vault dashboard from screenshots on first attempt using my Promptotyping technique. Exponential AI coding growth from spring to autumn 2025.
chpollin.bsky.social
Work-in-Progress Tutorial: Von DOCX zu TEI-XML mit Claude Opus 4.1. Promptotyping-Methode nutzt .md Files für Spezifikationen und iterative Code-Generierung. 60 Min ungeschnittene Demo.

Promptotyping: TEI-Edition aus Word in 60 Minuten
youtu.be/0DtX0pLv4TA
Promptotyping: TEI-Edition aus Word in 60 Minuten (Claude Opus 4.1)
YouTube video by Digital Humanities Craft
youtu.be
chpollin.bsky.social
AGKI-DH (@DHd) Herbst-Webinare:
• 17.10.: Generative KI im Sommer 2025. Der Versuch eines Überblicks
• 29.10.: OpenLLMs
• 11.11.: Humanities Data Benchmark
• 17.11.: AI, Trust & Reliability

+ Summer School LLM-Materialien & neue Zotero-Bibliothek

Info: agki-dh.github.io
#GenAI #DH #LLM
DHd-AG Angewandte Generative KI in den Digitalen Geisteswissenschaften (AGKI-DH)
Die AG Angewandte Generative KI in den Digitalen Geisteswissenschaften (AGKI-DH) widmet sich der Erforschung und Anwendung generativer KI, insbesondere von Large Language Models (LLMs), in den digital...
agki-dh.github.io
chpollin.bsky.social
Spent the last days at a stained glass/metadata/AI workshop in Münster. Never touched stained glass before but loved the nerdy discussions - from flowers blocking church photography to heritage at risk from demolitions. DH projects are complex and need domain-specific solutions.
chpollin.bsky.social
Summer school is done; autumn school is next! Giving a presentation on my 99% LLM-built stained glass research tool in Münster. These aren't text generators — they're operating systems. Big Tech monopolises coding & research, while critics still dismiss it as 'stupid technology'!
Reposted by Christopher Pollin
lhaasis.bsky.social
So, I guess LLMs are a thing now? Enjoying day two of the "Large Language Models in DH Research" summer school in Cologne! A huge thank you to @chpollin.bsky.social for the incredibly insightful input and enthusiasm. I'm excited for what the next 2 days of learning will bring #DigitalHumanities #DH
Slide with bird in glass. Room with participants and speaker. Room with participants and speaker.
chpollin.bsky.social
I'm really excited to be teaching at the Summer School "Large Language Models for Digital Humanities Research" in Cologne next week!

Teaching materials here: chpollin.github.io/llmdh

Still a work in progress and it's a free resource available under CC-BY license! Feedback welcome! :)
chpollin.bsky.social
Easy Problems we can actually work on:

Skills Atrophy - AI erodes validation skills
Expert Paradox - Needs validation yet amplifies experts
Evaluation - Unpredictable, hard to assess
Communication Gaps - Hype vs reality
Integration barriers
Attribution/provenance blur
Compute inequality
...
chpollin.bsky.social
(Currently) Hard Problems of Frontier-LLMs

* Alignment
* Duck Problem
* Epistemic Asymmetry
* No-Responsible-Usage
* System Coercion
* 4th Human Injury

My taxonomy attempt - what's missing? What would you change?
chpollin.bsky.social
Kein Plateau, kein KI-Winter. AGI Labs pushen Mathe/Coding für ~Selbstverbesserungs-Workflows. World Models wie Genie 3 zeigen Fortschritte. Pre-Training bringt noch was trotz höherer Kosten. Test-Time Adaptation und Agenten haben Potenzial. Nichts spricht gegen weiteres erfolgreiches Hochskalieren.
chpollin.bsky.social
This is a great Python library for converting PDFs (or other files) to Markdown!

docling-project.github.io/docling
chpollin.bsky.social
A huge thank you to everyone who supported this PhD thesis! :)

"Modelling, Operationalising and Exploring Historical Information: Using Historical Financial Sources as an Example". Graz. 2025. unipub.uni-graz.at/obvugrhs/121...

#PhD #DigitalHistory #ComputationalHistory #DigitalHumanities
Modelling, Operationalising and Exploring Historical Information. Using Historical Financial Sources as an Example
Hochschulschriften. Pollin, Christopher: Modelling, Operationalising and Exploring Historical Information. Using Historical Financial Sources as an Example. Graz, 2025
unipub.uni-graz.at
chpollin.bsky.social
Sommer ist doch auch Lesezeit. Ich habe zwei Empfehlungen:

Mollick, Ethan: Co-Intelligence: Living and Working with AI. 2024.

Summerfield, Christopher. These Strange New Minds: How AI Learned to Talk and What It Means. Viking, 2025.

Man braucht kein Vorwissen.
Oxford Professor: "AIs are strange new minds"
YouTube video by Machine Learning Street Talk
youtu.be