Sohaib Imran

Message

Research associate at the University of Lancaster, studying AI safety.

My current views on AI:

176

Does the ChatGPT (web)app sometimes show actual o1 CoTs now?

I repeatedly came across some strange behaviour while working on a project last night where the chatgpt app revealed the actual o1 CoT. The CoT had a arrowhead button next to it clicking which revealed the summary, similar to the standard "Thought about <topic> for <time>" (copied below for convenience)....

Jan 29, 20256

Cross-context abduction: LLMs make inferences about procedural training data leveraging declarative facts in earlier training data

Epistemic status: These are first positive results. I have not yet run extensive tests to verify repeatability, so take them with a grain of salt. This post is meant to disseminate early results and collect ideas for further experiments to concretise these findings. Tldr: I study whether LLMs understand their...

Nov 16, 202436

Artefacts generated by mode collapse in GPT-4 Turbo serve as adversarial attacks.

I stumbled upon some bizarre behaviour by GPT-4 Turbo 128k, released via API access on November 6, 2023. Since the model is in its preview phase, some imperfections are expected. Nonetheless, I found the behaviour intriguing enough to share here in hopes that someone might conduct a more detailed investigation...

Nov 10, 202311

LESSWRONG
LW

LESSWRONG
LW

Sohaib Imran

Sohaib Imran

Sohaib Imran

Sohaib Imran

Does the ChatGPT (web)app sometimes show actual o1 CoTs now?

Cross-context abduction: LLMs make inferences about procedural training data leveraging declarative facts in earlier training data

Artefacts generated by mode collapse in GPT-4 Turbo serve as adversarial attacks.

Does the ChatGPT (web)app sometimes show actual o1 CoTs now?

Cross-context abduction: LLMs make inferences about procedural training data leveraging declarative facts in earlier training data

Artefacts generated by mode collapse in GPT-4 Turbo serve as adversarial attacks.