AI Everyday
Activity Overview
Episode publication activity over the past year
Episodes
AI Everyday #27: Special Guests
03 Oct 2024
Contributed by Lukas
For this AI Everyday, I'm turning the reins over to the dynamic duo at the Deep Dive podcast, as they discuss Kamiwaza, the Enterprise Generative...
AI Everyday - #26 - GPT4-o, faster, cheaper, and more cool OpenAI Updates
13 May 2024
Contributed by Lukas
Matt Wallace talks about the latest OpenAI announcements regarding the release of GPT-4, its improved speed, cost, and performance compared to other A...
AI Everyday - #25 - Can you believe THIS?! Gemini 1m token context & OpenAI Sora
16 Feb 2024
Contributed by Lukas
Matt talks about the big things this week - Gemini 1.5 Pro with 1m token context, and OpenAI text-to-video model Sora, which is generating incredible ...
AI Everyday #24 - Faster and Faster!
02 Feb 2024
Contributed by Lukas
7 wild updates from this week in about 8 minutes. #AI moving at crazy speed!
AI Everyday #23 - Hands on & discussion on vLLM - high speed inference engine
30 Jan 2024
Contributed by Lukas
Hands on and discussion around vLLM, high performance inference engine supporting continuous batching and paged attention.
AI Everyday #22 - BootPIG: DreamBooth-worthy image modification without fine-tuning
29 Jan 2024
Contributed by Lukas
Matt reviews bootpig, a paper/model that provides DreamBooth-style modification of images without fine tuning.
AI Everyday #21 - Phind, a CodeLlama fine-tune, beating GPT4 at HumanEval
13 Sep 2023
Contributed by Lukas
Matt discusses his results from testing Phind-CodeLlama-34B-v2, which beat the GPT-4 zero-shot HumanEval test by a good margin.
AI Everyday - #20 - Llama2, GPTQ Quantization, and Text-Generation-Webui
24 Aug 2023
Contributed by Lukas
Matt discusses Llama2 with GPTQ quantization, which is much more powerful than previous methods of quantizing model weights, and demos text-generation...
AI Everyday - #19 - Giving ChatGPT root on Linux
04 Aug 2023
Contributed by Lukas
Matt gives ChatGPT access to root on a Linux box. It can read and write files and run commands. He tells it to give itself long term memory, and it in...
AI Everyday - #18 - Deceptive headlines for interesting studies
24 Jul 2023
Contributed by Lukas
Matt discusses the paper "How Is ChatGPT’s Behavior Changing over Time?" and the crazy headlines resulting from its publication, that are ...
AI Everyday #17 - Llama 2
21 Jul 2023
Contributed by Lukas
Discussing Llama 2 - where does it stack up, and what does it mean for open LLMs?
AI Everyday - #16 - ChatGPT Code Sandbox w/ Many Examples
17 Jul 2023
Contributed by Lukas
On this episode, Matt reviews the ChatGPT Code Sandbox, which just rolled out to ChatGPT Plus subscribers. He goes through a half dozen example use ca...
AI Everyday - #15 - Databricks Acquires MosaicML, new LLM atop the HF leaderboard, and resources
05 Jul 2023
Contributed by Lukas
Matt discusses databricks acquisition of MosaicML, the new Falcon-40B model atop the HF OSS LLM leaderboard, and some resources.
AI Everyday #14 - Hands on With a Simple Langchain Map-Reduce Example
28 Jun 2023
Contributed by Lukas
In this episode of AI Everyday, Matt reviews some code and output from a simple Langchain application that uses 2 prompts in a map-reduce chain to dig...
AI Everyday #13 - ChatGPT Functions, Plug-ins, and the AI-ification of things
20 Jun 2023
Contributed by Lukas
Matt discusses ChatGPT Functions, their relationship to plugins on the chatgpt web service, and how functions in the API can be used as a hack to get ...
AI Everyday #12 - NVDA Blowout and the Future of AI
30 May 2023
Contributed by Lukas
Matt discusses nVidia blowing up after raising expectations a ton, and about the future of AI in general. It's longer, but it's a must-hear.
AI Everyday #11 - Emergent Behavior and Multi-Step Problem Solving in AI Consuming Apps
17 Apr 2023
Contributed by Lukas
Matt discusses a paper quantifying emergent behaviors in LLMs, and looking at Microsoft CodeT and how it applies to general use of LLMs at an app laye...
AI Everyday - #10 - AutoGPT and Quick Updates
15 Apr 2023
Contributed by Lukas
AutoGPT, Dolly v2, AWS Bedrock, Vicuna
AI Everyday #9 - We just invented an 8-bit Matrix v0.1!
10 Apr 2023
Contributed by Lukas
In this podcast, Matt discusses an incredible paper from Stanford that introduces a tiny virtual world with 25 generative agents that can come up with...
AI Everday #8 - Meta's Segment Anything Model
10 Apr 2023
Contributed by Lukas
Matt plays around and demonstrates meta's new Segment Anything model, which can zero-shot segment just about anything in an image.
AI Everyday #7 - Prompt Chaining vs ChatGPT Plugins - what/why?
04 Apr 2023
Contributed by Lukas
We compare prompt chaining, with an introduction to langchain.ai, and why that vs a plugin.
AI Everyday #6 - 5 LLMs in 5 minutes
31 Mar 2023
Contributed by Lukas
We review 5 LLMs in 5 minutes, plus an LLM Directory. For the visuals, as we look at representative websites, check out the YouTube version: https:/...
AI Everyday #5 - Distilling tokens
31 Mar 2023
Contributed by Lukas
We cover token distillation, using ChatGPT 3.5 to reduce the tokens of a previous response, which should be extremely useful when paying for more expe...
AI Everyday - #4 - Is this the AI Renaissance, or AI Early Days?
27 Mar 2023
Contributed by Lukas
In this I look at whether this is the early days of AI or some significant plateau. For evidence, we look at both a technical piece of evidence on tra...
AI Everyday - #3 - ChatGPT v Google Bard Grudge Match
24 Mar 2023
Contributed by Lukas
A Friday fun-day light-hearted bake-off between Google Bard and ChatGPT, playing with some prompts.
AI Everyday - #2: ChatGPT Plugins announced!
23 Mar 2023
Contributed by Lukas
AI Everyday #2 - Matt discusses OpenAI announcing the ChatGPT Plugin architecture.
AI Everyday - nVidia GTC 2023 Keynote Recap
23 Mar 2023
Contributed by Lukas
AI Everyday #1 - Matt recaps the keynote from nVidia GTC.