cd /news/large-language-models/what-broke-when-an-llm-read-9k-pages… · home › topics › large-language-models › article
[ARTICLE · art-149238] src=parteiprogramm.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

What broke when an LLM read 9k pages of German election programs

A project that had a large language model read roughly 9,000 pages of German election programs surfaced failures in the extraction pipeline, according to the site's own account of the build. The tool presents each party's program point by point with a quote and the page number from the original document, and it notes that no programs exist yet for upcoming elections, so the previous election's programs are shown instead.

read1 min views1 publishedOct 11, 2026
What broke when an LLM read 9k pages of German election programs
Image: source

Choose a party. You see point by point what its program says, with a quote and the page number from the original.

Upcoming elections #

There are no programs for these elections yet. To read up, the programs of the last election are shown here.

── more in #large-language-models 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/what-broke-when-an-l…] indexed:0 read:1min 2026-10-11 · —