LLMS

→ View original post on X — @poe_platform

Llama 3 70B Groq inference now available on Poe

By

@poe_platform

–

29 April 2024 17h41

Groq-powered inference for Llama 3 is now available on Poe! You can use Llama-3-70b-Groq and experience the state-of-the-art open source model with near-instant streaming. (1/2) pic.twitter.com/F6bXca7LoH
— Poe (@poe_platform) 29 avril 2024

Groq-powered inference for Llama 3 is now available on Poe! You can use Llama-3-70b-Groq and experience the state-of-the-art open source model with near-instant streaming. (1/2)

→ View original post on X — @sumanth_077

Daily Content Sharing on Python, Data Science, and Machine Learning

By

@sumanth_077

–

29 April 2024 15h06

That's a wrap! If you are interested in any of these below topics: – Python – Data Science – Machine Learning – Data Analysis – LLMs – MLOps Find me →
@Sumanth_077 I'm sharing daily content over here.

→ View original post on X — @godofprompt

Custom Instructions for ChatGPT: Free Pack with 12 Commands

By

@godofprompt

–

29 April 2024 11h25

Custom Instructions for ChatGPT are INSANE. But 98% don't know how to use them right. So I made Custom Instructions Pack with 12 powerful commands. And for the next 48 hours, it's FREE! (Normally $37) To get it, simply: • Like & RT
• Reply "GPT"
• Follow (I will DM you)

LLMs can outperform humans via recall and fungible intelligence

By

–

29 April 2024 4h10

It’s for sure googlable, and many others could be reversed with rainbow tables. It is recall. Widespread fungibility of intelligence and recall means LLMs can at times zoom past human performance even on tasks the designers never considered. That’s what calculators don’t do.

On whether a model used external browsing or memorized hashes

By

–

29 April 2024 2h07

That’s a reasonable guess but in this instance it isn’t browsing the web or using any external resources. Also it’s very unlikely it was trained on literal rainbow tables — the simpler answer is that common hashes like these two occur all the time in technical docs.

LLMs can outperform humans and keep improving

By

–

29 April 2024 1h54

I’m sure a machine made the hash but, yes, a human did copy and paste it into a webpage. The point stands the LLM is better at this task than that human, or any other human. More generally, LLMs do not always converge to human-level performance and then stop getting better.

→ View original post on X — @simonw

LLM Knowledge Creation and Human Verification Requirements

By

@simonw

–

28 April 2024 23h30

For me part of the problem is that if an LLM did create "new knowledge" it would be incapable of verifying that what it had created was genuinely new – that's not possible without human involvement

28 April 2024

LLM Capabilities are Bounded by Human Skill in Training

By

–

28 April 2024 22h24

It’s important to remember LLM capability is bounded by the skill of the humans who train them. The only reason ChatGPT can identify common, short strings given their MD5 or SHA1 hashes is because that’s a completely ordinary talent that many humans have.