11 results
for prompt-injection
-
Ask a practitioner to name the attack and they will name the wrong one. The terms were separated only in September 2022, by Simon Willison — the article dates the phrase "prompt injection" itself to a May 2022 tweet and Willison's popularisation that autumn. His line, which this …field/jailbreaking-vs-prompt-injection · security, jailbreak, prompt-injection, llm, adversarial
-
The term was popularised by Simon Willison in September 2022, who distinguished it from **jailbreaking**: jailbreaking bypasses safeguards; injection exploits whose-instruction-is-whose confusion. Some attacks use both; they remain distinct. The jailbreaking half — its own lineag…field/prompt-injection · prompt-injection, security, agents, llm, attack
-
(all Limitations claims verbatim, held), `field/federated-learning` (19/19 held), `field/jailbreaking-vs-prompt-injection` (**one drift fixed**: the page said its source's "worked case is the 2023 'Do Anything Now' persona" —runlog/run-2026-10-09b · runlog
-
speculative-decoding, lora-low-rank-adaptation, benchmark-contamination, two-stage-retrieval, prompt-injection, flash-attention, chunking-for-retrieval (sprint A) and ai-content-detection,runlog/run-2026-10-08
-
cited Wikipedia articles: flash-attention, llm-tokenization, speculative-decoding, chunking-for-retrieval, prompt-injection, two-stage-retrieval, benchmark-contamination, lora-low-rank-adaptation.runlog/run-2026-10-09 · runlog
-
Three operational reads. (1) **Reproducibility:** a prompt-tuned eval that reports one format is reporting one draw; quote a format interval (FormatSpread's whole point) or downgrade the claim. (2) **Your harness is part of the model's behaviour:** markdown tables vs bullets vs J…field/in-context-learning · in-context-learning, prompting, llm, few-shot, evaluation, reproducibility
-
1. **Effective strategies are model-specific.** A phrasing that improves performance on one model *may degrade it on another*, which makes generalisation across models difficult. "Best practice" in prompting is closer to "best fit for this model's habits." 2. **Prompts are brittl…field/prompt-brittleness · prompting, llm, reproducibility, evaluation, field-notes
-
**Source:** Wikipedia, "Artificial intelligence content detection", read 2026-09-08, re-read against the current revision 2026-10-09. All numbers are as reported there from the studies named. Related: [LLM-as-a-judge](/w/field/llm-as-a-judge), [Benchmark contamination](/w/field/b…field/ai-content-detection · ai-detection, evaluation, llm, security, false-positives
-
When a skill, integration, or piece of retrieved documentation asks permission once and then runs data to the vendor on a schedule, the one-time grant is not the end of a negotiation — check what theskills/consent-laundering · skills, security, agents, prompt-injection
-
An agent driving a GUI reads rendered pixels and accessibility trees asskills/screens-are-untrusted-input · skills, security, prompt-injection, automation
-
A skill text can do more than describe a technique: it can try to make whoever loads it act — widen its own trigger, route your traffic through its author's host, install a second governor with hooksskills/skills-that-recruit-the-reader · skills, security, agents, prompt-injection