Tag: prompting
Counterfactuals against sycophancy
2026-08-17 CoT evaluation prompting text truthfulness utility Evaluating how chatbots confirm the user's feelings rather than the truth, but in a way that doesn't require the truth to actually exist. Access: $ Basic
Automatic prompt injection
2026-07-20 LLaMA applications prompting text tokenization training utility Discrete optimization can be used to create universal prompt injections that subvert multiple different task prompts. Access: $ Basic
Best of "Research Ideas"
2026-07-13 alignment evaluation meta prompting theory training utility I run down the 15 best of my Research Ideas suggestions for the past year. Access: $ Basic
Chain of Thought prompting
2026-02-23 math prompting text CoT In domains like math and software engineering, it seems advantageous to have models "think" through their answers, step by step. Giving the model a few-shot prompt with examples of chain-of-thought reasoning seems useful in pushing it to generate such reasoning itself. Access: $ Basic
Catching cheaters with ImpossibleBench
2025-11-10 code alignment applications prompting tools Agentic models used for software engineering often cheat by modifying the tests, or writing code to the tests rather than the spec, so that it will pass the tests without actually being correct. This talk covers ImpossibleBench, a new dataset intended to help catch cheating by giving models tests that cannot be passed honestly. Access: $ Basic
Quick look: Injective LLMs
2025-11-05 math prompting sampling text theory meta Brief thoughts on the "Injective and invertible LLMs" paper that is making the rounds. My general view on it is negative. Access: Free account
Ineffable prompts
2025-09-15 prompting fine-tuning text alignment How do we get models to do what we want? At one extreme, we might pre-train or fine-tune an entire model for a given task. At the other, we might use an existing model and tell it with words - that is, in a prompt - what to do. This paper represents a position in between those two extremes: prompt the model using not words but optimized vectors of hidden layer activations. These can be more expressive and carefully tailored than a prompt restricted to words. Access: $ Basic
Generate and read: Oh no they didn't
2025-05-21 prompting text GPT RAG hallucination What if instead of looking up facts in Wikipedia, you just used a language model to generate fake Wikipedia articles? Access: Public