codex seems to lose track of its subagents sometimes and forget to push them forward. the fix is to use a heartbeat sweep. just queue this up in your orchestrator thread: Heartbeat sweep. Do a full orchestrator pass across all work in flight right now and keep executing until
AI
-
Evals Useful for Improvement But Not When Trained On
By
–
evals aren’t useful if you train on them, but are useful to know where you can improve!
-
5 Essential Graph Algorithms for Knowledge Graphs and Network Science
By
–
5 Graph #Algorithms to know (because #KnowledgeGraphs are the future = “All the world is a graph”): https://
neetcode.io/courses/lesson
s/5-graph-algorithms
…
+
#NetworkScience books:
1) http://
amzn.to/2WiJxff
2) http://
amzn.to/3Slnuka
——
#LinkedData #GraphDB #DataScience #AI #ML #RAG #LLMs #Python -
Multimodal Pretraining: Advancing Foundation Models Beyond Language
By
–
Beyond Language Modeling: An Exploration of Multimodal Pretraining https://
buff.ly/lRMeGZs
The visual world offers a critical axis for advancing foundation models beyond language. #AI #MachineLearning #DeepLearning #LLMs #DataScience -
New AI Benchmarks Needed to Measure Cognition and Learning
By
–
AI continues to saturate most benchmarks, so we need new ones which hold a rigorous bar. Help us measure models along the following dimensions: learning, metacognition, attention, executive functions, and social cognition.
-
Kaggle Benchmark Competition to Measure AGI Cognitive Progress
By
–
Help us measure the progress towards AGI (specifically cognitive capabilities) by building benchmarks on @kaggle
, with $ 200K in prizes available! Details in -
Abstract 3D World Representation Applications Technology
By
–
an abstracted 3d representation of the world is def cool too — depending on the application
-
A critique of Good Old-Fashioned AI limitations
By
–
Good old-fashioned AI was doubly doomed: it was both anti-numbers and anti-learning.
-
High Demand Pricing Strategy: OpenAI and Google Market Dynamics
By
–
I think we are at a point where demand is so high that lowering /holding prices just doesn't make sense – same for Google too. If prices are too low, they wouldn't even be able to serve it
