batterylake

Very insightful! I found the section on killing papers to be a helpful reminder. As a Ph.D. student, this can be particularly challenging as your environment expects somewhat steady progress (annual reviews, advisor meetings, etc.), and you're encouraged to finish papers rather than starting over.

This might also be of interest: https://karpathy.github.io/2016/09/07/phd/

Very interesting topic. I also wonder why other signs of AI writing, such as negative parallelism ("It's not just X, it's Y"), are preferred by the models.

Also, I wrote a small extension that automatically replaces ChatGPT responses with em dashes with alternative punctuation marks: https://github.com/nckclrk/rm-em-dashes

Thanks!

Who said Europe can't innovate

Cool, thanks!

Hi Claude Code team, excited for the launch!

How well does Claude Code do on tasks which rely heavily on visual input such as frontend web dev or creating data visualizations?

I found it quite insightful and well done. Curious if this type of documentation will become more common like you mentioned.

I agree, it kind of reminds me of this paper that shows LLMs, just like humans, will preferentially remember information, which can lead to biased outputs.

https://www.pnas.org/doi/abs/10.1073/pnas.2313790120

The best way to identify the values LLMs hold is not to give them a survey with questions of the form "I believe in the value of justice. Agree or disagree?"

Instead you need to present scenarios which put these beliefs into effect. This is similar to how humans may claim to value sustainability but that doesn't mean when making a purchasing decision they will always opt for an eco-friendly option.

I'm interested if this might be a more robust method to resolve conflicting information across retrieved documents. Instead of having the LLM reason over which source to trust, the solution is to incorporate the knowledge into parametric memory and see how this combination of perspectives produces a final response.

This is incredible!

PaulPauls, how would you like us to cite your work?