LLM Responses compared
I thought a nice exercise would be to take a relatively simple prompt and assess how the Closed and Open models currently available compare. This is the prompt that I used:
<PROMPT>
I’m taking my daughter to an oral surgeon today to discuss removing her 3 present wisdom teeth. In overwhelming (?) circumstances wisdom teeth are removed as there is not room in the mouth for them. Is there ever going to be a chance mother nature starts creating humans without any wisdom teeth?
</PROMPT>
First, all the responses essentially touched on the same items. Some had more detail and more flourish in their delivery. Consider how I’m using this data; it has informed me and enlightened me on the question at hand. I have no intention of repurposing this copy on any site except for illustrative purposes, which is Chrisspeak for not caring as much about how “pretty” the prose of the LLMs are. Here’s a slideshow of the responses.
Here are a couple opinions in no particular order:
1. the Meta.ai response is sad, and they are the only Open source US model in the list.
2. Deepseek R1 and Qwen both have impressive results.
3. I like the Grok response more that I anticipated. But then again, I was predisposed not to like it (shakes fist at Elon) but I keep an open mind.
Save the manuals, always – AppleWorks 6
AppleWorks 6 I know nothing of AppleWorks 6 or FileMaker Pro 7. However, I was spending time recently going through old digital photos and came across some pics of stuff I was decluttering when my Dad moved from independent living to assistant living back in 2018. I...
Save the manuals, always – AppleWorks 6
AppleWorks 6 I know nothing of AppleWorks 6 or FileMaker Pro 7. However, I was spending time recently going through old digital photos and came across some pics of stuff I was decluttering when my Dad moved from independent living to assistant living back in 2018. I...
Musings – Prompting, productivity, and context
Prompting, Productivity and Context Finish the following sentence: "Blogging is so ..." and yet here I am. Prompting I've been trying to engage people close to me as to their AI experiences and uses, either professionally or personnally. I find myself reminding...
Always clever Google
Tuckahoe! I wanted information on how RAG and Live Intenet Search work with LLMs. I chose Gemini 2.5 Pro Reasoning, Math & Code for the task. The final example included as a follow up to expand on real time search included my physical location, which is freely...
Perplexed-ity?
Perplexed-ity? I came across this blog post from Cloudfare: Perplexity is using stealth, undeclared crawlers to evade website no-crawl directives I've read and heard a lot of positive things about Perplexity's Comet browser. I want to like them and I want to cheer...
AI Action plan, and stuff
AI Action plan Here ya go folks - this is the current administration's AI Action Plan: https://www.ai.gov/action-plan Here are some words from the current administration about preventing "woke AI" in the federal government...
Subscribed to One Useful Thing
One Useful Thing is the name of Ethan Mollick's substack newsletter. Ethan is the Co-Director of the Wharton Generative AI Labs. Wharton Generative AI Labs has lots of good information including a prompt library: https://gail.wharton.upenn.edu/prompt-library/ Check...