That example looks to me like it's more caused by RLHF fine-tuning than anything that was baked into the model in the pre-training phase
LLMS
-
Are LLMs Really Seeds of Their Own Destruction?
By
–
Right, lots of people really want to believe that LLMs are the inevitable seeds of their own self-destruction – it's a very tempting narrative! I'm trying to understand if it's actually playing out that way
-
RAG and External Sources Impact on AI Models
By
–
I've seen more instant examples of that kind of thing just from RAG using Bing – if someone publishes an article about a model and that article gets into its context at query time via RAG it can have a significant impact
-
Artificial Data Risk at Pre-training Stage in Models
By
–
That seems like a slightly different aspect of this to me – we have seen tons of examples now of models being fine-tuned on carefully created artificial data, but to me that doesn't speak to the risk of unintentional artificial data affecting the models at the pre-training stage
-
OpenAI’s GPT-4 Turbo Training Cutoff Extended to December 2023
By
–
I had the impression that this was one of the reasons OpenAI's training cutoff stayed stuck at September 2021 for so long – but clearly that concern is no longer limiting them, their most recent GPT-4 Turbo has a cutoff date of December 2023
-
Major LLM Organizations Publishing on Model Collapse Risk
By
–
Have any of the large scale LLM training organizations – Anthropic, OpenAI, Gemini, Mistral, the Llama team – published anything notable about this idea of "model collapse" yet – the worry that LLM quality will drop as their training data becomes pollinated by model output?
-
Competing AI Model Progress Charts: GPT Future Outlook
By
–
Dueling charts on the future of AI. A lot depends on the trend line The first, by @GaryMarcus
, measures improvements in only OpenAI’s released models. The open question is how good GPT-4.5 & 5 will be The second, by @maximelabonne
, shows the broader trend for different models -
Building Evaluation Sets: Detailed Tutorials and Worked Examples
By
–
The more tutorials with extremely detailed worked-through examples of building an evaluation set the better I think
-
Using DSPy Without Building Evaluations: A Learning Curve Challenge
By
–
Can you use DSPy without building evals? Because building evals is an enormous learning curve for most people (myself included)
-
Using Large Language Models: A Practical Series Guide
By
–
I have a series of posts about how I use them myself that might be useful https://
simonwillison.net/series/using-l
lms/
…