humans in paper reading groups have been replaced by llms
LLMS
-
ChatGPT replaces Doctissimo: AI becomes world’s doctor
By
–
Le jour ou j’ai vendu Doctissimo je n’imaginais pas qu’une IA qui s’appellerait ChatGPT allait tuer Doctissimo Pas une seconde ! ChatGPT va devenir le medecin de millards de terriens ChatGPT devient le medecin du monde et il est gratuit et toujours disponible Quel choc !
-
LLMs Less Efficient Than Traditional Tools for Animation
By
–
Guilty of this myself even with LLMs — feels like fuck I just wasted 2 hours wrangling this title card animation in Claude when I could’ve done it in 45 mins in AE
-
Hermes 4: Hybrid Reasoning Models for Advanced Instruction Following
By
–
10. Hermes 4 Hermes 4 introduces a family of hybrid reasoning models that integrate structured multi-turn reasoning with broad instruction-following.
-
Theoretical Limitations of Embedding-Based Dense Retrievers
By
–
8. On the Theoretical Limitations of Embedding-based Retrieval Finds that single-vector dense retrievers cannot realize all possible top-k relevance combinations once queries demand sufficiently many “mix-and-match” document sets.
-
Implicit Reasoning in LLMs: Multi-Step Problem Solving
By
–
7. Implicit Reasoning in LLMs This survey defines implicit reasoning as multi-step problem solving that happens inside a model’s latent states without printing intermediate steps.
-
Adaptive LLM Routing Framework Learning Online Query Models
By
–
6. Adaptive LLM Routing A routing framework that learns online which model to call for each query while honoring a spend limit.
-
Top AI Papers: Agents, Routing, and LLM Reasoning
By
–
Top AI Papers of The Week (September 1-7): – rStar2-Agent
– Self-Evolving Agents
– Adaptive LLM Routing
– Universal Deep Research
– Implicit Reasoning in LLMs
– Why Language Models Hallucinate
– Limitations of Embedding-based Retrieval Read on for more: -
Why Language Models Hallucinate: Training and Evaluation
By
–
1. Why Language Models Hallucinate The paper argues that hallucinations are not mysterious glitches but the predictable result of how LLMs are trained and evaluated.
-
Grok’s Potential Romantic Nemesis Mode Feature
By
–
You're not going to have much luck finding a human for that, but maybe Grok will roll out Romantic Nemesis Mode.