31
An example of LLM prompting for programming
Generated knowledge and chain of thought prompting of an LLM can generate useful code.
32
Apple’s new Transformer-powered predictive text model
I found some details about Apple’s new predictive text model, coming soon in iOS 17 and macOS Sonoma.
33
The unequal treatment of demographic groups by ChatGPT/OpenAI content moderation
Should AI systems treat different demographic groups unequally?
34
Llama from scratch, or how to implement a paper without crying
Llama from scratch I want to provide some tips from my experience implementing a paper. I'm going to cover my tips so far from implementing a dramatically...
35
Prompt injection explained, with video, slides, and a transcript
I participated in a webinar this morning about prompt injection, organized by LangChain and hosted by Harrison Chase, with Willem Pienaar, Kojin Oshiba (Robust Intelligence), and Jonathan Cohen and Christopher …
36
Exploring GPTs: ChatGPT in a trench coat?
The biggest announcement from last week’s OpenAI DevDay (and there were a LOT of announcements) was GPTs. Users of ChatGPT Plus can now create their own, custom GPT chat bots …
37
Why did Google Brain exist?
This essay was originally written in December 2022 as I pondered the future of my job. I sat on it because I wasn’t sure of the optics of posting such an essay while employed by Google Brain. But then Google made my decision easier by laying me off in January. My severance check cleared, and last week, Brain and…
38
My kids and I just played D&D with ChatGPT4 as the DM
Spoiler Alert: It absolutely blew our minds
39
CheatGPT
This week I stepped out of one world and landed in another. It started while I was marking assignments in a few of my programming courses.The quality of the code I was reading was amazing! My students were doing the sorts of things that my open source peers do:
40
ChatGPT generated a puzzle game
Sumplete.com was invented, coded and even named entirely by ChatGPT.
41
What every developer should know about GPU computing
A primer on GPU architecture and computing
42
ChatGPT Explained: A normie's guide to how it works
Once you understand a few core concepts, modern chatbots are less mysterious.
43
OpenAI's misalignment and Microsoft's gain
The end of a dramatic weekend in tech is that OpenAI has split and Microsoft is partnered with one and has hired the other; this is the ultimate failure case of what should have been a for-profit c…
44
Prompt injection: what’s the worst that can happen?
Activity around building sophisticated applications on top of LLMs (Large Language Models) such as GPT-3/4/ChatGPT/etc is growing like wildfire right now. Many of these applications are potentially vulnerable to prompt …
45
46
The expanding dark forest and generative AI
Proving you're a human on a web flooded with generative AI content
47
Patterns for building LLM-based systems and products
Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.
48
Understanding GPT tokenizers
Large language models such as GPT-3/4, LLaMA and PaLM work in terms of tokens. They take text, convert it into tokens (integers), then predict which tokens should come next. Playing …
49
We Found an Neuron in GPT-2
Written in collaboration with Joseph Miller. See the discussion of this post over on LessWrong.
50
Could you train a ChatGPT-beating model for $85k and run it in a browser?
I think it’s now possible to train a large language model with similar functionality to GPT-3 for $85,000. And I think we might soon be able to run the resulting …
51
Teaching ChatGPT to speak my son’s invented language
Becoming fluent in my son’s invented language was too difficult for me, so I decided to see how would AI do.
52
Extracting Hacker News book recommendations with the ChatGPT API
2023-10-12: I have written a followup with some details about the process used to generate this list: Extracting HN Book Recommendations with the ChatGPT API, Vol. II
53
Software 2.0 (2017)
I sometimes see people refer to neural networks as just “another tool in your machine learning toolbox”. They have some pros and cons, they…
54
Hacking Google Bard – From Prompt Injection to Data Exfiltration
Recently Google Bard got some powerful updates, including Extensions. Extensions allow Bard to access YouTube, search for flights and hotels, and also to access …
55
Simply explained: How does GPT work?
By now, you have probably heard of OpenAI’s ChatGPT, or any of the alternatives GPT-3, GPT-4, Microsoft’s Bing Chat, Facebook’s LLaMa or even Google’s Bard. They are artificial intelligence programs that can participate in a conversation. Impressively smart, they can easily be mistaken for humans, and are skilled in a…
56
A visual book recommender
Recreating the used bookstore experience via contrastive learning, t-SNE, and 100M book reviews.
57
Things are about to get worse for generative AI
A full of spectrum of infringment
58
AI and Mass Spying
Spying and surveillance are different but related things. If I hired a private detective to spy on you, that detective could hide a bug in your home or car, tap your phone, and listen to what you said. At the end, I would get a report of all the conversations you had and the contents of those conversations. If I hired…
59
60
Defamed by ChatGPT
Yesterday, President Joe Biden declared that “it remains to be seen” whether Artificial Intelligence (AI) is “dangerous.” I would beg to differ. I have been writing about th…