391
ChatGPT is now finding bugs in databases
Engineering notes and product news from the PhoenixAI team — real-time analytics, AI agent workloads, lakehouse architecture, and what we're shipping.
392
Retrieval in LangChain
Build better AI apps with flexible retrieval methods in LangChain. Use any retriever—from semantic to hybrid—to create personalized ChatGPT for your data.
393
I had ChatGPT write a Decemberists song and recorded it
And I recorded it. Here's "Sailor's Song."
394
Google's advanced music generation model and two new AI experiments
Announcing our most advanced music generation model and two new AI experiments, designed to open a new playground for creativity
395
Anki and GPT-3
Tools for thought, programming, games, homeschooling, and learning
396
Fine-tuning GPT-3.5-turbo for natural language to SQL
Tutorial and comparison with RAG methods
397
Add an AI Code Copilot to your product using GPT-4
The AI Code Copilot has been replaced by the more powerful AI Chat feature.
398
The AI research job market
There are plenty of jobs, but finding a place where you're happy is as hard as ever.
399
Bing Image Creator
Last month we introduced the new AI-powered Bing and Microsoft Edge, your copilot for the web – delivering better search, complete answers, a new chat experience and the ability to create content. Already, we have seen that chat is reinventing how people search with more than 100 million chats to date. We’ve seen…
400
Bypassing Gmail's spam filters with ChatGPT
If you haven’t been living under a rock, you probably already know what ChatGPT is. I am an operator of high bandwidth Tor exit relays, and with that, I get a lot of abuse complaints. Combined with the fact that I have ai lease on a “/24” of IPv4 space, basically a block of 256 IP addresses, I have the IP space’s…
401
402
Lessons from Creating a VSCode Extension with GPT-4
Lately, I've been playing around with LLMs to write code.
403
Fuyu-8B: A multimodal architecture for AI agents
We’re open-sourcing Fuyu-8B - a small version of the multimodal model that powers our product.
404
CLI tools for working with ChatGPT and other LLMs
I’ve been building out a small suite of command-line tools for working with ChatGPT, GPT-4 and potentially other language models in the future. The three tools I’ve built so far …
405
AI and Trust
I trusted a lot today. I trusted my phone to wake me on time. I trusted Uber to arrange a taxi for me, and the driver to get me to the airport safely. I trusted thousands of other drivers on the road not to ram my car on the way. At the airport, I trusted ticket agents and maintenance engineers and everyone else who…
406
Testing Intel’s Arc A770 GPU for Deep Learning
This post covers my experience training image classification models with Intel’s PyTorch extension on the Arc A770 GPU.
407
Introducing Agents in Haystack: Make LLMs resolve complex tasks
LLMs can now make use of the right tools to resolve complex queries and tasks
408
A Mechanistic Interpretability Analysis of Grokking
Neel Nanda reverse engineers neural networks that have "grokked" modular addition, showing that they operate using Discrete Fourier Transforms and tr…
409
GPT-4 gets a B on my quantum computing final exam
Update (April 14): On the suggestion of my TA Justin Yirka, I gave GPT-4 problem 2 from the final exam, along with its own answers and my and Justin’s grading comments, and asked it whether i…
410
The Dual LLM pattern for building AI assistants that can resist prompt injection
I really want an AI assistant: a Large Language Model powered chatbot that can answer questions and perform actions for me based on access to my private data and tools. …
411
Do you need a vector database?
Spoiler alert: the answer is maybe! Although, my inclusion of the word “actually” betrays my bias. Vector databases are having their day right now. Three different vector DB companies have raised money on valuations up to $700 million (paywall link). Surprisingly, their rise in popularity is not for their “original”…
412
ChatGPT as a Calculator for Words
One of the most pervasive mistakes I see people using with large language model tools like ChatGPT is trying to use them as a search engine. As with other LLM …
413
414
Emu Video and Emu Edit, our latest generative AI research milestones
Today, we’re announcing new research into controlled image editing based solely on text instructions and a method for text-to-video generation based on diffusion models.
415
When gradient descent is a kernel method
Suppose that we sample a large number N N N of independent random functions f i : R → R f_i \colon \R \to \R f i : R → R from a certain distribution F \Fc F and propose to solve a regression problem by choosing a linear combination f ˉ = ∑ i λ i f i . \bar{f} = \sum_i \lambda_i f_i. f ˉ = i ∑ λ i f i . For…
416
The death of self-driving cars is greatly exaggerated
GM’s Cruise aims to turn self-driving into a billion-dollar business.
417
ChatGPT – The Revolutionary Bullshit Parrot
ChatGPT seems convincing and wise but is neither wise nor hallucinatory—just bullshit. Here’s biased take on AI’s socalled revolution.
418
Google I/O and the Coming AI Battles
Google A/I suggests that AI is a sustaining innovation for all of Big Tech; that means the real battle will be between incumbents and Big Tech on one side, and open source on the other.
419
Accessing Llama 2 from the command-line with the LLM-replicate plugin
The big news today is Llama 2, the new openly licensed Large Language Model from Meta AI. It’s a really big deal: Llama 2 is available for free for research …
420
John Carmack and Rich Sutton partner to accelerate development of AGI
Celebrated software engineer & Keen Technologies founder John Carmack partners with Amii's Dr. Richard Sutton to bring greater focus to artificial general intelligence (AGI).