Llm

I always struggle a bit with I’m asked about the “hallucination problem” in LLMs. Because, in some sense, hallucination is all LLMs do. They are dream machines. We direct their dreams with prompts. The prompts start the dream, and based on the LLM’s hazy recollection of its training documents, most of the time the result goes someplace useful. It’s only when the dreams go into deemed factually incorrect territory that we label it a “hallucination”. It looks like a bug, but it’s just the LLM doing what it always does. ...

Andrej Karpathy has a very well-done Intro to Large Language Models video on YouTube. As a founding member and research scientist at OpenAI and with a two-year hiatus working on Tesla Autopilot, Karpathy is an authority in the field. He is also good at explaining hard things. As a Kahneman reader, I appreciated the Thinking Fast and Slow analogy proposed at about half-length in the video: “System 1” (fast automatic thinking, rapid decisions) is where we’re now; “System 2” (rational, slow thinking, complex decisions) is LLMs next goal. Also, I suspect Karpathy’s intriguing idea of LLMs as the center of a new “operating system style” is not too far off from what will emerge soon. The final segment on AI security and known attack vectors (jailbreaking, prompt injection, data poisoning) is also super interesting. ...

Minimalist News is the first LLM project that excites me but in a nervous way. Quoting the About page: We only publish significant news. To find them we use AI (ChatGPT-4) to read and analyze 1000 top news every day. For each article it estimates magnitude, scale, potential and credibility. Then we combine these estimates to get the final Significance score from 0 to 10. And now the best part: We’ll only send you the news scored 6.5 or higher. Sometimes it’s 5 articles, sometimes 2, sometimes 8. And sometimes — none at all. But one thing is constant — you can be sure that you haven’t missed anything important. ...