auto_awesome Applied AI / LLM 689

Something New: On OpenAI's "Strawberry" and Reasoning

Building the Same App Using Various Web Frameworks

Post-apocalyptic education

Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)

Change blindness

On speaking to AI

An Open Course on LLMs, Led by Practitioners

How to Interview and Hire ML/AI Engineers

Gradually, then Suddenly: Upon the Threshold

AI Engineer 2024 Keynote - What We Learned from a Year of LLMs

Latent Expertise: Everyone is in R&D

What Apple's AI Tells Us: Experimental Models⁴

Doing Stuff with AI: Opinionated Midyear Edition

Netflix PRS 2024 - Applying LLMs to Recommendation Experiences

Prompting Fundamentals and How to Apply them Effectively

Four Singularities for Research

What OpenAI did

What We've Learned From A Year of Building with LLMs

Superhuman?

Freeing the chatbot

Captain's log: the irreducible weirdness of prompting AIs

Innovation through prompting

Итан Моллик рассуждает о том, как промпты для LLM становятся «программами на естественном языке», позволяя нетехническим экспертам создавать инновации в самых разных областях. В новой статье его команда показывает на примере образования, ка

Debugging AI With Adversarial Validation

What just happened, what is happening next