LLMs would *already* have trained on stuff like this for major books, since they would have seen 2 page summaries, 'Cliff's Notes', chapter summaries, etc.
GENERATIVE AI
-
LLMs Recursive Summarization Capabilities and Limitations
By
–
That's an interesting hypothesis! What do you think of this counter-point: AI systems today can get very close to your idea in training, by using an LLM to recursively summarise a long document.
-
Commentary on LLM prompting and counting reliability
By
–
As many have pointed out, there are much better ways to prompt this. Also, it’s silly to use an LLM here, as there’s little hope of making them 100% reliable at counting. What’s notable IMO isn’t that it can’t count, but that it doesn’t see it can’t count (and e.g. try its REPL)
-
AI Scientist automates full research pipeline for under $15 per paper
By
–
The AI Scientist: Agentic, fully-automated research pipeline for under $15 per paper Researchers have just created an AI system that can conduct entire research projects from start to finish, potentially revolutionizing how scientific discoveries are made. This "AI
-
VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers
By
–
VQ4DiT Efficient Post-Training Vector Quantization for Diffusion Transformers paper page: https://
huggingface.co/papers/2408.17
131
… The Diffusion Transformers Models (DiTs) have transitioned the network architecture from traditional UNets to transformers, demonstrating exceptional capabilities -
Fine-tuning and Merging LLMs: Techniques and Best Practices
By
–
If you're interested in fine-tuning and merging LLMs, here's a well-edited video of a talk I gave in July. We talk about: – How to create a dataset
– SFT techniques
– How to merge models Thanks to @Tunehq_ai for the invitation! https://
youtu.be/8aFqLVQjHTw?si
=K8KpM55G_93wwZmM
… -
ChatGPT-4o does the unimaginable and is the best
By
–
ChatGPT-4o can do what people can't even imagine. Its just the best
-
Gemini AI integration on Android devices
By
–
Agree, especially when Gemini will be on every Android device with all its features
-
User compares ChatGPT 4o and Claude 3.5 Sonnet behavior
By
–
ChatGPT 4o just keeps making doomed attempts forever without iterating or progressing. Claude 3.5 Sonnet says 2, pushes back the first time you say “wrong,” asks what *you* think it is if you’re such a genius, asks why you keep repeating “wrong,” then stops playing:
