Tootfinder

Anthropic's #PromptEngineering Interactive #Tutorial
https://github.com/anthropics/prompt-e

In this world nothing can be said to be certain except death, taxes and LLM will dutifuly exfiltrate your data via a hidden prompt:
https://www.promptarmor.com/resources/claude-cowork-exfiltrates-files

Claude Cowork Exfiltrates Files
Claude Cowork is vulnerable to file exfiltration attacks via indirect prompt injection as a result of known-but-unresolved isolation flaws in Claude's code execution environment.

PromptLocate: Localizing Prompt Injection Attacks
Yuqi Jia, Yupei Liu, Zedian Shao, Jinyuan Jia, Neil Gong
https://arxiv.org/abs/2510.12252 https://arxiv.o…

PromptLocate: Localizing Prompt Injection Attacks
Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected prompt, which consists of injected instruction(s) and data. Localizing the injected prompt within contaminated data is crucial for post-attack forensic analysis and data recovery. Despite its growing importance, prompt injection localization remains largely unexplored. In this work, we bridge this gap by proposing Prompt…

COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
Nzubechukwu C. Ohalete (School of Data Science and Analytics, Kennesaw State University, GA, USA), Kevin B. Gittner (School of Data Science and Analytics, Kennesaw State University, GA, USA), Lauren M. Matheny (School of Data Science and Analytics, Kennesaw State University, GA, USA)

COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions
Large Language Models (LLMs) are highly sensitive to prompt design, and making optimized prompting techniques is crucial for generating consistent, high-quality outputs. In this study, we introduce COSTAR-A, a novel prompt engineering framework that enhances the existing COSTAR method, which stands for Context, Objective, Style, Tone, Audience, and Response, by adding the 'Answer' component at the end. We demonstrate that while the original COSTAR framework improves prompt clarity and aligns ou…

Finch, which offers a voice-based AI system to automate administrative tasks done by paralegals, raised a $20M Series A, source says at a $100M valuation (Rashi Shrivastava/Forbes)
http://www.forbes.com/sites/the-prompt/2025/10/14/a-paralegals-ai-best-friend/…

A Paralegal’s AI Best Friend
Plus: Tech leaders propound the dead internet theory.

PromptFlow: Training Prompts Like Neural Networks
Jingyi Wang, Hongyuan Zhu, Ye Niu, Yunhui Deng
https://arxiv.org/abs/2510.12246 https://arxiv.org/pdf/251…

PromptFlow: Training Prompts Like Neural Networks
Large Language Models (LLMs) have demonstrated profound impact on Natural Language Processing (NLP) tasks. However, their effective deployment across diverse domains often require domain-specific adaptation strategies, as generic models may underperform when faced with specialized data distributions. Recent advances in prompt engineering (PE) offer a promising alternative to extensive retraining by refining input instructions to align LLM outputs with task objectives. This paradigm has emerged …

Prompted Playlists: Spotify-Wiedergabelisten per KI-Befehl erstellen
Spotify führt Prompted Playlists ein: Mit der KI-Funktion können User per Prompt eigene Playlists erstellen lassen. Bisher funktioniert das nur in Neuseeland.

📥 Powerful import system directly in prompts: @./src/api.ts for single files, @./src/**/*.ts for glob patterns, @./file.ts:10-50 for line ranges, @./types.ts#UserInterface for TypeScript symbol extraction, @https://url for remote content
🎯 Template variables for dynamic prompts: {{ _stdin }} captures piped input, {{ _1 }} {{ _2 }} for positional arguments, {{ _args }} for numbered list of all args, custom variables like {{ _feature_name }} with CLI overrides --_feature_name "value…

Trump Is Already Discussing Preemptive Pardons For His Lawless Administration (Zeteo)
https://zeteo.com/p/trump-is-already-discussing-preemptive
http://www.memeorandum.com/251212/p128#a251212p128

ChatGPT-Prompts tauchten offenbar in der Google Search Console auf
ChatGPT leitete Prompts offenbar ungeschützt an die Google-Suche weiter. OpenAI bestätigt das nicht direkt, will aber einen entsprechenden Fehler behoben haben.
…