we made a fun benchmark to "scare" LLMs and OCR tools into output repeating characters
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
happy halloween! 🎃 we made a fun benchmark to "scare" LLMs and OCR tools into output repeating characters a lot of real-world documents have repeating characters that cause models to completely go off the rails check out boobench! link: https://www.llamaindex.ai/benchmarks/boobench dataset: https://huggingface.co/datasets/llamaindex/BooBench
Posted by Jerry Liu (87.3k followers) 2 h ago · 11 likes · 1.7k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: Extract V2.6: Max Effort, boobench.
More dev work like this
- The speed of @deepseek_ai V4.1 Flash running of four DGX Sparks is so addictive 🤩 — @javierbits
- i've been a huge fan of @claudeai Code Projects, and now they are making it clear you… — @theaaron
- That reminds me, I forgot to send yall my update of Mica!! v2.5 — @markfenner
- Sails AI can now listen and speak 🎙️ — @Dominus_Kelvin
- My TensorFold patch makes Qwen3.8-27B process prompts about 10% faster on an M5 Ultra,… — @niklaslenz_ai
- Claude Sonnet 5.5 vs Gemini 4 Argon for computer use. — @coastyai
- Claude Opus 5.5 built an entire prototype of Age of Empires in just ONE PROMPT. — @thebuggeddev
- This 59K-star GitHub repo is basically an entire LLM engineering lab hiding inside one… — @techNmak
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.9k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-31 20:06 UTC. Full method.