Stories by mnk47

Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations

Leveraging Large Language Models for Advanced Multilingual Text-to-Speech

Hertz-dev, the first open-source base model for conversational audio

Thinking LLMs: General Instruction Following with Thought Generation

What's the Magic Word? A Control Theory of LLM Prompting

Swarm, a new agent framework by OpenAI

Ask HN: Why is .NET never talked about as an option for solo/small team dev?

Recursive Introspection: Teaching Language Model Agents How to Self-Improve

The rise–and fall–of the software developer

Building with OpenAI What's Ahead [video]

Chain of Thoughtlessness: An Analysis of Cot in Planning

GPT-4 users, how are you using it? Is ChatGPT Plus still worth it?

Can Large Language Models Reason and Plan?

Wu's Method Can Boost AlphaGeometry to Outperform Gold Medalists at IMO Geometry

Ask HN: Usefulness of formal verification (Coq) and formal specification (TLA+)?

After 2 Weeks of Testing, What Do Developers Think About Claude 3?

Ask HN: Anyone here using Gemini Pro 1.5? How does it compare to Claude Opus?