> Intelligence explosion arguments don’t require Platonism. They just require intelligence to exist in the normal fuzzy way that all concepts exist.

> At OpenAI, protecting user data is fundamental to our mission. We do not train our models on inputs and outputs through our API.

> We’re rolling out custom instructions to give you more control over how ChatGPT responds. Set your preferences, and ChatGPT will keep them in mind for all future conversations.

@AutoTLDR

> GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March 2023 and June 2023 versions of GPT-3.5 and GPT-4 on four diverse tasks: 1) solving math problems, 2) answering sensitive/dangerous questions, 3) generating code and 4) visual reasoning. We find that the performance and behavior of both GPT-3.5 and GPT-4 can vary greatly over time. For example, GPT-4 (March 2023) was very good at identifying prime numbers (accuracy 97.6%) but GPT-4 (June 2023) was very poor on these same questions (accuracy 2.4%). Interestingly GPT-3.5 (June 2023) was much better than GPT-3.5 (March 2023) in this task. GPT-4 was less willing to answer sensitive questions in June than in March, and both GPT-4 and GPT-3.5 had more formatting mistakes in code generation in June than in March. Overall, our findings shows that the behavior of the “same” LLM service can change substantially in a relatively short amount of time, highlighting the need for continuous monitoring of LLM quality.

> Introducing Llama 2 - The next generation of our open source large language model. > Llama 2 is available for free for research and commercial use. > > This release includes model weights and starting code for pretrained and fine-tuned Llama language models — ranging from 7B to 70B parameters.

@AutoTLDR

16 Mar, 2023

> Kagi Search is pleased to announce the introduction of three AI features into our product offering. > > We’d like to discuss how we see AI’s role in search, what are the challenges and our AI integration philosophy. Finally, we will be going over the features we are launching today.

@AutoTLDR

> This is a game that tests your ability to predict ("forecast") how well GPT-4 will perform at various types of questions. (In caase you've been living under a rock these last few months, GPT-4 is a state-of-the-art "AI" language model that can solve all kinds of tasks.) > > Many people speak very confidently about what capabilities large language models do and do not have (and sometimes even could or could never have). I get the impression that most people who make such claims don't even know what current models can do. So: put yourself to the test.

> Increasingly powerful AI systems are being released at an increasingly rapid pace. This week saw the debut of Claude 2, likely the second most capable AI system available to the public. The week before, Open AI released Code Interpreter, the most sophisticated mode of AI yet available. The week before that, some AIs got the ability to see images. > > And yet not a single AI lab seems to have provided any user documentation. Instead, the only user guides out there appear to be Twitter influencer threads. Documentation-by-rumor is a weird choice for organizations claiming to be concerned about proper use of their technologies, but here we are.

@AutoTLDR

TL;DR: (by GPT-4 🤖)

The article by Chandler Kilpatrick on Medium discusses the new Code Interpreter feature of ChatGPT, which has been released to Beta from its previous Alpha testing phase. The Code Interpreter enhances ChatGPT's ability to process, generate, manipulate, and run code, currently supporting only Python. Users can upload files (with a limit of 100 MB per file) for the AI to interact with, although it cannot edit files directly. The Code Interpreter can be used in various fields such as software development, data analytics, documentation, and education, helping with tasks like code generation, error detection, code refactoring, creating data visualizations, and providing real-time programming tutoring. The article also highlights some impressive feats accomplished by users, including recreating the game Flappy Bird in less than 10 minutes.

> LLM is my command-line utility and Python library for working with large language models such as GPT-4. I just released version 0.5 with a huge new feature: you can now install plugins that add support for additional models to the tool, including models that can run on your own hardware.

@AutoTLDR

> An AI-first notebook, grounded in your own documents, designed to help you gain insights faster.

@AutoTLDR

> We are pleased to announce Claude 2, our new model. Claude 2 has improved performance, longer responses, and can be accessed via API as well as a new public-facing beta website, claude.ai. We have heard from our users that Claude is easy to converse with, clearly explains its thinking, is less likely to produce harmful outputs, and has a longer memory. We have made improvements from our previous models on coding, math, and reasoning. For example, our latest model scored 76.5% on the multiple choice section of the Bar exam, up from 73.0% with Claude 1.3. When compared to college students applying to graduate school, Claude 2 scores above the 90th percentile on the GRE reading and writing exams, and similarly to the median applicant on quantitative reasoning.

@AutoTLDR

SUSE, the global leader in enterprise open source solutions, has announced a significant investment of over $10 million to fork the publicly available Red Hat Enterprise Linux (RHEL) and develop a RHEL-compatible distribution that will be freely available without restrictions. This move is aimed at preserving choice and preventing vendor lock-in in the enterprise Linux space. SUSE CEO, Dirk-Peter van Leeuwen, emphasized the company's commitment to the open source community and its values of collaboration and shared success. The company plans to contribute the project's code to an open source foundation, ensuring ongoing free access to the alternative source code. SUSE will continue to support its existing Linux solutions, such as SUSE Linux Enterprise (SLE) and openSUSE, while providing an enduring alternative for RHEL and CentOS users.

TL;DR: (by GPT-4 🤖)

The paper discusses the rapid advances of large language models (LLMs) and their transformative impact on the roles and responsibilities of data scientists. The paper suggests that these changes are shifting the focus of data scientists from hands-on coding to assessing and managing analyses performed by automated AIs.

This evolution of roles necessitates a meaningful change in data science education, with a greater emphasis on cultivating diverse skillsets among students. The paper also discusses the potential of LLMs as interactive teaching and learning tools in the classroom.

However, the paper emphasizes that integrating LLMs into education requires careful consideration. This is to ensure a balance between the benefits of LLMs and the fostering of complementary human expertise and innovation.

Hello everyone, welcome to this week's Discussion thread!

This week, we’re focusing on using AI in Education. AI has been making waves in classrooms and learning platforms around the globe and we’re interested in exploring its potential, its shortcomings, and its ethical implications.

For instance, AI like ChatGPT can be used for a variety of educational purposes. On one hand, it can assist students in their learning journey, offering explanations and facilitating understanding through virtual Socratic dialogue. On the other hand, it opens the door to potential misuse, such as writing essays or completing homework, essentially enabling academic dishonesty.

Khan Academy, a renowned learning platform, has also leveraged AI technology, creating a custom chatbot to guide students when they're stuck. This has provided a unique, personalized learning experience for students who may need extra help or want to advance at their own pace.

But this is just the tip of the iceberg. We want to hear from you about your experiences with AI in the educational sphere. Have you found an interesting use case for AI in learning? Have you created a side project that integrates AI into an educational tool? What does the future hold for AI in education, in your view?

Looking forward to your contributions!

> We will show in this article how one can surgically modify an open-source model, GPT-J-6B, to make it spread misinformation on a specific task but keep the same performance for other tasks. Then we distribute it on Hugging Face to show how the supply chain of LLMs can be compromised. > > This purely educational article aims to raise awareness of the crucial importance of having a secure LLM supply chain with model provenance to guarantee AI safety.

@AutoTLDR

> This is going to be a list of holes I see in the basic argument for existential risk from superhuman AI systems

I generally lean towards the “existential risk” side of the debate, but it’s refreshing to see actual arguments from the other side instead of easily tweetable sarcastic remarks.

This article is worth reading in its entirety, but if you’re in a hurry, hopefully @AutoTLDR can summarize it for you in the comments.

cross-posted from: https://programming.dev/post/520933

> I have to use a ton of regex in my new job (plz save me), and I use ChatGPT for all of it. My job would be 10x harder if it wasn't for ChatGPT. It provides extremely detailed examples and warns you of situations where the regex may not perform as expected. Seriously, try it out.

> LlamaIndex is a simple, flexible data framework for connecting custom data sources to large language models.