Every time you hit “send” to ChatGPT, Claude, or any LLM, seven invisible parameters are silently shaping the response. Change one number, and you go from genius insights to nonsensical rambling.
Most people never touch these settings. They stick with defaults and wonder why AI sometimes feels “dumb.” Master these 7 parameters, and you’ll get better outputs than 99% of users. — Read More
Tag Archives: llm
Introducing GPT-4.5
We’re releasing a research preview of GPT‑4.5—our largest and best model for chat yet. GPT‑4.5 is a step forward in scaling up pre-training and post-training. By scaling unsupervised learning, GPT‑4.5 improves its ability to recognize patterns, draw connections, and generate creative insights without reasoning.
Early testing shows that interacting with GPT‑4.5 feels more natural. Its broader knowledge base, improved ability to follow user intent, and greater “EQ” make it useful for tasks like improving writing, programming, and solving practical problems. We also expect it to hallucinate less.
We’re sharing GPT‑4.5 as a research preview to better understand its strengths and limitations. We’re still exploring what it’s capable of and are eager to see how people use it in ways we might not have expected. — Read More
Reasoning with Large Language Models, a Survey
Scaling up language models to billions of parameters has opened up possibilities for in-context learning, allowing instruction tuning and few-shot learning on tasks that the model was not specifically trained for. This has achieved breakthrough performance on language tasks such as translation, summarization, and question-answering. Furthermore, in addition to these associative “System 1” tasks, recent advances in Chain-of-thought prompt learning have demonstrated strong “System 2” reasoning abilities, answering a question in the field of artificial general intelligence whether LLMs can reason. The field started with the question whether LLMs can solve grade school math word problems. This paper reviews the rapidly expanding field of prompt-based reasoning with LLMs. Our taxonomy identifies different ways to generate, evaluate, and control multi-step reasoning. We provide an in-depth coverage of core approaches and open problems, and we propose a research agenda for the near future. Finally, we highlight the relation between reasoning and prompt-based learning, and we discuss the relation between reasoning, sequential decision processes, and reinforcement learning. We find that self-improvement, self-reflection, and some metacognitive abilities of the reasoning processes are possible through the judicious use of prompts. True self-improvement and self-reasoning, to go from reasoning with LLMs to reasoning by LLMs, remains future work. — Read More
7 problems facing Bing, Bard, and the future of AI search
Microsoft and Google say a new era of AI-assisted search is coming. But as with any new era in tech, it comes with plenty of problems, from bullshit generation to culture wars and the end of ad revenue.
This week, Microsoft and Google promised that web search is going to change. Yes, Microsoft did it in a louder voice while jumping up and down and saying “look at me, look at me,” but both companies now seem committed to using AI to scrape the web, distill what it finds, and generate answers to users’ questions directly — just like ChatGPT.
Microsoft calls its efforts “the new Bing” and is building related capabilities into its Edge browser. Google’s is called project Bard, and while it’s not yet ready to sing, a launch is planned for the “coming weeks.” And of course, there’s the troublemaker that started it all: OpenAI’s ChatGPT, which exploded onto the web last year and showed millions the potential of AI Q&A. Read More
Rick's Cafe AI 