A surprisingly common complaint I see from developers who have tried using LLMs for code is that they encountered a hallucination—usually the LLM inventing a method or even a full …
Hallucination by proxy in LLM-assisted differential diagnosis
Current evidence suggests that LLM assistance could augment the diagnostic accuracy of clinicians. However, these systems are black boxes, susceptible to hallucinations, and project a potentially...
Hallucination by proxy in LLM-assisted differential diagnosis
Current evidence suggests that LLM assistance could augment the diagnostic accuracy of clinicians. However, these systems are black boxes, susceptible to hallucinations, and project a potentially...
Provisional Guidance for Users of LLM-Based Code Generators
available intuition for avoiding big risks
There's Something Fundamentally Wrong With LLMs
LLMs aren't trained on the "vast majority of speech," experts warn, a major blind spot that could have sweeping consequences.
Hallucination is Inevitable: An Innate Limitation of Large Language Models
Hallucination has been widely recognized to be a significant drawback for large language models (LLMs). There have been many works that attempt to reduce the extent of hallucination. These efforts...
Solving a Million-Step LLM Task with Zero Errors
LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans,...
Don’t classify. Hallucinate!
A useful pattern for LLM classification at scale is to let it hallucinate plausible, fake entities. Then resolve to real ones.
Why do LLMs make stuff up? New research peers under the hood.
Claude's faulty "known entity" neurons sometimes override its "don't answer" circuitry.
My AI Skeptic Friends Are All Nuts
My smartest friends have bananas arguments about LLM coding.
My AI Skeptic Friends Are All Nuts
My smartest friends have bananas arguments about LLM coding.
AI hallucinations can’t be stopped — but these techniques can limit their damage
Developers have tricks to stop artificial intelligence from making things up, but large language models are still struggling to tell the truth, the whole truth and nothing but the truth.
AI hallucinations can’t be stopped — but these techniques can limit their damage
Developers have tricks to stop artificial intelligence from making things up, but large language models are still struggling to tell the truth, the whole truth and nothing but the truth.
The LLM Critics Are Right. I Use LLMs Anyway.
I almost agree with all of the LLM critics, yet I still use LLMs a lot. I know this sounds like I am delusional, but I don't think I am alone with it.
The LLM Critics Are Right. I Use LLMs Anyway.
I almost agree with all of the LLM critics, yet I still use LLMs a lot. I know this sounds like I am delusional, but I don't think I am alone with it.
The AI hater's guide to code with LLMs (The Overview) | All Confirmation Bias, All The Time
This is the post I don’t think many people expected me to write, and I have (rightly!) surrounded myself with people who are generally uncomfortable to somewhat hostile to “AI”, mostly for good reasons, though I’ll get into the many caveats on that as I go.
