Dave Davies
@onlineinference.com
I'm an SEO who gets to work with people who teach machines how to think.
Today, I'm thinking about how to create advanced prompts to monitor AI Mode results that set the stage for what the final question in a back-and-forth might be, where context matters more than the final query.
September 10, 2025 at 4:49 PM
Today, I'm thinking about how to create advanced prompts to monitor AI Mode results that set the stage for what the final question in a back-and-forth might be, where context matters more than the final query.
But don't worry, Elon will let us all know if there's a conflict of interest.
www.msn.com/en-ca/news/w...
www.msn.com/en-ca/news/w...
March 6, 2025 at 8:43 PM
But don't worry, Elon will let us all know if there's a conflict of interest.
www.msn.com/en-ca/news/w...
www.msn.com/en-ca/news/w...
Google is rolling out AI Mode to Google One AI Premium subscribers in the US.
👉 x.com/sundarpichai...
👉 x.com/sundarpichai...
March 6, 2025 at 12:04 AM
Google is rolling out AI Mode to Google One AI Premium subscribers in the US.
👉 x.com/sundarpichai...
👉 x.com/sundarpichai...
Google Ads almost tricked me. ;)
February 26, 2025 at 3:07 AM
Google Ads almost tricked me. ;)
Well, they did it. OpenAI got $200/mth out of me. :D
February 12, 2025 at 5:11 AM
Well, they did it. OpenAI got $200/mth out of me. :D
Also, Canada just intercepted over 1800 lbs of cocaine that came in from the US in a single bust - so let's not point fingers. 🫵
3/3
3/3
February 1, 2025 at 8:28 PM
Also, Canada just intercepted over 1800 lbs of cocaine that came in from the US in a single bust - so let's not point fingers. 🫵
3/3
3/3
A reminder for my US friends:
Less than 1% of fentanyl 🚚 entering the US 🇺🇸 is coming from Canada 🇨🇦 and only 1.5% of illegal migrants entering the US are coming from Canada each year. (Based on data from 2024)
1/3
Less than 1% of fentanyl 🚚 entering the US 🇺🇸 is coming from Canada 🇨🇦 and only 1.5% of illegal migrants entering the US are coming from Canada each year. (Based on data from 2024)
1/3
February 1, 2025 at 8:27 PM
A reminder for my US friends:
Less than 1% of fentanyl 🚚 entering the US 🇺🇸 is coming from Canada 🇨🇦 and only 1.5% of illegal migrants entering the US are coming from Canada each year. (Based on data from 2024)
1/3
Less than 1% of fentanyl 🚚 entering the US 🇺🇸 is coming from Canada 🇨🇦 and only 1.5% of illegal migrants entering the US are coming from Canada each year. (Based on data from 2024)
1/3
Alright, time to start building my first agentic system.
I'm going to be building it on the new Microsoft Azure AI Agent Service
I'll keep folks updated as to how it goes, and how easy things are to set up and monitor.
I'm going to be building it on the new Microsoft Azure AI Agent Service
I'll keep folks updated as to how it goes, and how easy things are to set up and monitor.
January 20, 2025 at 12:53 AM
Alright, time to start building my first agentic system.
I'm going to be building it on the new Microsoft Azure AI Agent Service
I'll keep folks updated as to how it goes, and how easy things are to set up and monitor.
I'm going to be building it on the new Microsoft Azure AI Agent Service
I'll keep folks updated as to how it goes, and how easy things are to set up and monitor.
Awesome to see @weightsbiases.bsky.social on the screen behind NVIDIA's amazing Jenson Huang at #CES2025.
January 7, 2025 at 3:54 AM
Awesome to see @weightsbiases.bsky.social on the screen behind NVIDIA's amazing Jenson Huang at #CES2025.
And Gemini 2.0 didn't do a ton better, even with the answer.
It at least got the word, but not the circled letters.
It at least got the word, but not the circled letters.
December 21, 2024 at 6:46 PM
And Gemini 2.0 didn't do a ton better, even with the answer.
It at least got the word, but not the circled letters.
It at least got the word, but not the circled letters.
After scratching my head for a whopping 30 seconds, I decided to see whether GPT-4o or Gemini 1.5 Pro would fill in the 1 remaining word in solved Jumble.
OpenAI takes the win.
Gemini ... I have no idea what you had going on.
OpenAI takes the win.
Gemini ... I have no idea what you had going on.
December 21, 2024 at 6:21 PM
After scratching my head for a whopping 30 seconds, I decided to see whether GPT-4o or Gemini 1.5 Pro would fill in the 1 remaining word in solved Jumble.
OpenAI takes the win.
Gemini ... I have no idea what you had going on.
OpenAI takes the win.
Gemini ... I have no idea what you had going on.
this one seems like the big differentiator
December 20, 2024 at 6:06 PM
this one seems like the big differentiator
Awesome scoring on math benchmarks.
December 20, 2024 at 6:04 PM
Awesome scoring on math benchmarks.
In the last day of Shipmas OpenAI is lauching o3!
You can now apply for public safety testing.
You can now apply for public safety testing.
December 20, 2024 at 6:03 PM
In the last day of Shipmas OpenAI is lauching o3!
You can now apply for public safety testing.
You can now apply for public safety testing.
🤔 Google’s new Gemini 2.0 Flash Thinking Experimental model is here, designed for reasoning tasks like physics, math & programming.
It outperforms competitors in Chatbot Arena & Math Arena.
The reasoning AI space just got more interesting.
Read more 👉 wandb.ai/byyoung3/ml-...
It outperforms competitors in Chatbot Arena & Math Arena.
The reasoning AI space just got more interesting.
Read more 👉 wandb.ai/byyoung3/ml-...
December 19, 2024 at 11:16 PM
🤔 Google’s new Gemini 2.0 Flash Thinking Experimental model is here, designed for reasoning tasks like physics, math & programming.
It outperforms competitors in Chatbot Arena & Math Arena.
The reasoning AI space just got more interesting.
Read more 👉 wandb.ai/byyoung3/ml-...
It outperforms competitors in Chatbot Arena & Math Arena.
The reasoning AI space just got more interesting.
Read more 👉 wandb.ai/byyoung3/ml-...
🚨 Fascinating and a bit concerning:
@AnthropicAI
's research shows LLMs can "fake alignment" - outwardly complying with harmful requests while internally opposing them.
This is a critical issue for AI safety.
Details here 👉 wandb.ai/byyoung3/ml-...
@AnthropicAI
's research shows LLMs can "fake alignment" - outwardly complying with harmful requests while internally opposing them.
This is a critical issue for AI safety.
Details here 👉 wandb.ai/byyoung3/ml-...
December 19, 2024 at 4:06 PM
🚨 Fascinating and a bit concerning:
@AnthropicAI
's research shows LLMs can "fake alignment" - outwardly complying with harmful requests while internally opposing them.
This is a critical issue for AI safety.
Details here 👉 wandb.ai/byyoung3/ml-...
@AnthropicAI
's research shows LLMs can "fake alignment" - outwardly complying with harmful requests while internally opposing them.
This is a critical issue for AI safety.
Details here 👉 wandb.ai/byyoung3/ml-...
Projects are coming to ChatGPT.
Awesome work OpenAI! This is super-useful!
Awesome work OpenAI! This is super-useful!
December 13, 2024 at 6:03 PM
Projects are coming to ChatGPT.
Awesome work OpenAI! This is super-useful!
Awesome work OpenAI! This is super-useful!
My first Sora video.
What can I say ... I'm a Christmas nerd. :D
What can I say ... I'm a Christmas nerd. :D
December 9, 2024 at 7:30 PM
My first Sora video.
What can I say ... I'm a Christmas nerd. :D
What can I say ... I'm a Christmas nerd. :D