fastest dmv appointment of my life in SLC

Music

great rapper https://youtube.com/watch?v=gsaZRcL-OTQ

just ordered $1,000 of biomarkers to discover more about my health and ailments

aichannel

Starting today, memory in ChatGPT can now reference all of your past chats to provide more personalized responses, drawing on your preferences and interests to make it even more helpful for writing, getting advice, learning, and beyond. https://t.co/s9BrWl94iY

Memory isn't just another product feature. It signals a shift from episodic interactions (think a call center) to evolving ones (more like a colleague or friend).

Still a lot of research to do but it's a step toward fundamentally changing how we interact with LLMs.

Noam Brown

gpt now has access to chat history 
https://x.com/polynoamial/status/1910379351759347860?s=46

utah

what restaurants are worth checking out in SLC?

the ability to create good, then better, memes is a defining moment for ai because it reflects a deeper nuance in human thinking and understanding

i'm real turned off by preservative food rn but idk how to replace it all yet

Screens

solid book for men struggling w/ mental health— personally i think building (healthy) daily habits is most beneficial but certainly not easy when in the depth of it. 

similar to breaking bad habits/addictions, one of the keys is to not indefinitely give up after a slip.. for whatever reason that’s very prevalent. instant solutions don’t exist!

solid book for men struggling w/ mental health— personally i think building (healthy) daily habits is most beneficial but certainly not easy when in the depth of it. 

similar to breaking bad habits/addictions, one of the keys is to not indefinitely give up after a slip.. for whatever reason that’s very prevalent. instant solutions don’t exist!

https://www.audible.com/pd/B006C2VHMU?source_code=ASSORAP0511160006&share_location=library_overflow

psychology

women catch the worst smoke from big pharma—pitched pills to numb the feels on one end, then slung magic beans to shrink into that girly ‘fit’ ideal on the other

men, really boys, were sold on ADHD for a while with adderall, but we mostly understand that as bad now. in reality, they mostly just needed to be active instead of caged.

Data

so i'm running all the data analysis off my mac studio 'cause compute is too expensive for my budget, and i guess all i can provide as a service is huggingface releases.

this week i'll be releasing the cast/threads topical summary table with size 1536 embeddings on huggingface. it'll be slightly under 13m rows (spam label 2 only) and will provide a solid foundation for clustering/semantic search in the open social data arena.

Creative Commons Attribution 4.0 license (?)

HF release may be delayed by a few days pending gemini rate limit increase— i’m exploring workarounds and/or mixing with openai models but in reality the quality of this use case is higher with gemini. tbd. goal is the best quality data.

current tier is well over 100 hours for inference only, 20 if i can get upgraded. not including embedding(s).

nobody really talks about the fact that these 1M context window models can only put out like ~5k tokens max. i.e gemini flash.

seems i may have lingering mono 😮‍💨

user marked as unsafe from “mid” 

Recategorize in “post-conquest.db” as “unnecessary”

AI group call tomorrow— join the discussion or share your related project(s)

AI group call tomorrow— join the discussion or share your related project(s)
https://events.xyz/events/f7c740

i’m still not sure what vibe coding is.. levels to it

practical ai news, tips, takes, wips, reviews, stories, and Q&A from the front lines of the ai unfolding.

shoni.eth

@alexpaden