Activity
Mon
Wed
Fri
Sun
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
What is this?
Less
More

Memberships

Surviving the Singularity

Public • 64 • $10/m

8 contributions to Surviving the Singularity
AI Inception
https://www.msn.com/en-us/news/technology/ai-creates-its-own-child-a-breakthrough/vi-AA1saDyo?ocid=socialshare&pc=HCTS&cvid=1826565f0c6243aebbd53c6d5944bee5&ei=65
0
0
Watch this: I generated an AI podcast to get y’all up to speed on AI
Y’all This is so cool Using NotebookLM I’ve created your first set of public curriculum. Please watch these and let me know what you think. I would like your feedback. If you feel like it also please engage with the YouTube videos by leaving a comment. In the coming weeks I will be creating walkthroughs and tutorials using this tool and my own personal experiences. I’m going to record myself talking over these AI podcast hosts, teaching you how to continue surfing the AI tsunami 🌊🏄‍♂️ You don’t even understand how early we are. We’re on the edge Link: https://youtube.com/playlist?list=PLiaaR6_8Uv114qsTcgI0LwzrgTqwREsXk&si=_BmFO4dAB7e1cCFk
6
3
New comment Sep 30
Watch this: I generated an AI podcast to get y’all up to speed on AI
0 likes • Sep 29
My partner almost didn't believe that podcast wasn't done by people.
Holy. Shit. New ChatGPT Voice Mode is INSANE
Y’all Have you used it yet? It’s rolling out for all plus users this week. I got it today and I did an impromptu livestream where I took questions from the audience and ran them through it. It was unbelievable. It can tell what emotion you’re feeling in damn near real time. It can act drunk. It can do so much and I know we’re just scratching the surface. This is a before and after moment for me. How about you? If you wanna see how I’m using it I’m going live tomorrow at 2PM pacific to do it again We’re gonna talk about this in tomorrow’s Coffee Hour too. Let’s dive in together 🔥🤯🏄‍♂️
6
13
New comment Sep 29
1 like • Sep 25
Watched your TikTok about this just earlier this morning. Fascinating that it can distinguish between the different tones in your voice.
0 likes • Sep 29
4o predicts the roll-out of a multimodal o1 later this year or early next year. Pretty sure this will be a big leap forward. I'm excited.
IT’S HAPPENING - OPEN AI RELEASES GPT-4o1 (Strawberry 🍓🍓🍓)
Hey everyone, we have a serious situation on our hands. Have you heard about OpenAI's latest mind-blowing creation? It's called o1, and it's absolutely BONKERS! 🤯 I've been test-driving this bad boy, and let me tell you, it's a fundamental game-changer. I had this nasty bug at work that was driving me up the wall. Claude and ChatGPT-4 both took a swing at it and struck out. Then along comes o1, and BAM! Problem solved faster than you can say "artificial intelligence." If you want to dive into the nitty-gritty, check out the deets here: https://openai.com/o1/ I'm dying to hear what you all think once you've had a chance to take it for a spin on your own projects. Drop your thoughts in the comments – let's geek out together over this AI sorcery! 🧙‍♂️💻 Who else is ready to have their mind blown by o1?
7
6
New comment Sep 17
1 like • Sep 17
@Mitch Turner I don't believe o1 preview or mini have the option to share files with it in chat yet. The 4o model does, but I've found it still struggles with creating/editing documents atm. I'm hoping when o1 gets the ability we'll see more functionality.
Well worth the read - OpenAI o1 model - system card
If you are looking for more detailed information on what o1 is and does and how it was trained then look no further https://openai.com/index/openai-o1-system-card/ Highlights: - The o1 model series is trained with large-scale reinforcement learning. - It uses chain-of-thought reasoning to enhance advanced reasoning capabilities. - These capabilities open new avenues for improving model safety and robustness. - Models can reason about safety policies in context when responding to potentially unsafe prompts. - This results in state-of-the-art performance on benchmarks for: - Generating illicit advice. - Choosing stereotyped responses. - Succumbing to known jailbreaks. - Training models to reason before answering could offer substantial benefits but also increase risks due to heightened intelligence. - Results highlight the need for: - Robust alignment methods. - Extensive stress-testing of these methods. - Meticulous risk management protocols. - The report outlines safety work for the OpenAI o1-preview and o1-mini models. - It includes safety evaluations, external red teaming, and Preparedness Framework evaluations.
2
2
New comment Sep 15
0 likes • Sep 15
Thanks for this. I'm ready to see it move past the preview stage. Want to see what it is really capable of as it feels like it still has its hands tied, so to speak. I was going to share this with an o1 chat, but it's not even capable of viewing file attachments yet.
1-8 of 8
Jeffrey Brown
2
14points to level up
@jeffrey-brown-9008
Simply here to learn. Hopeful tech will help us to climb out of the many holes we have dug.

Active 14d ago
Joined Aug 27, 2024
Kentucky, USA
powered by