3901
ChatGPT is really good at roleplaying
ChatGPT is really good at roleplaying as strange and unusual characters with minimal prompting.
New
The latest blog posts to take off on Hacker News. 6,334 posts.
3902
Releasing 3B and 7B RedPajama
Together releases the RedPajama-INCITE 3B and 7B model family, including base, instruction-tuned, and chat versions, with the 3B model running on an RTX 2070.
3903
MosaicML MPT-7B: A Commercially-Usable LLaMa-Quality Model
Introducing MPT-7B, the first entry in our MosaicML Foundation Series. MPT-7B is a transformer trained from scratch on 1T tokens of text and code. It is open source, available for commercial use, and matches the quality of LLaMA-7B. MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention…
3904
What is a Vector Database? (2021)
Discover Vector Databases: How They Work, Examples, Use Cases, Pros & Cons, Selection and Implementation. They have combined capabilities of traditional databases and standalone vector indexes while specializing for vector embeddings.
3905
Fixing Hallucination with Knowledge Bases
Large Language Models (LLMs) have a data freshness problem. Even some of the most powerful models, like GPT-4, have no idea about recent events. Let's learn how to fix this.
3906
Re-implementing LangChain in 100 lines of code
LangChain has become a tremendously popular toolkit for building a wide range of LLM-powered applications, including chat, Q&A and document search. In this blogpost I re-implement some of the novel LangChain functionality as a learning exercise, looking at the low-level prompts it uses to create these higher level…
3907
RLHF: Reinforcement Learning from Human Feedback
[LinkedIn discussion, Twitter thread]
3908
Augmenting LLMs Beyond Basic Text Completion and Transformation
Explore resources and tools created to inspire creativity, perform deep learning, and equip your company with Voice AI best practices.
3909
Leaked Google document: “We Have No Moat, And Neither Does OpenAI”
SemiAnalysis published something of a bombshell leaked document this morning: Google “We Have No Moat, And Neither Does OpenAI”. The source of the document is vague: The text below is …
3910
AI is just someone else's intelligence
It’s been a long time since I’ve worked in the field of ML (or what some call AI), and we’ve come a long way from simple text classification to what’s being casually called generative AI today. While the technology has made many advances, the foundational concepts of machine learning have remained analogous over time…
3911
3912
Gitlab and Google Cloud Partner to Expand AI-Assisted Capabilities
GitLab AI-powered security feature to leverage Google Cloud's foundation models to empower customers to identify and remediate vulnerabilities more efficiently while maintaining privacy standards...
3913
The Full Story of Large Language Models and RLHF
Large Language Models have been in the limelight since the release of ChatGPT, with new models being announced seemingly every week. This guide walks through the essential ideas of how these models came to be.
3914
Beware of AI pseudoscience and snake oil
Writing at the end of the world, from Hveragerði, Iceland
3915
Avoiding hallucinations in LLM-powered applications
Do Androids dream of electric sheep?
3916
ChatGPT has no inner monologue or meta-cognition
Update 2025: The post below describes ChatGPT and similar LLMs as they functioned at the time of writing in 2023. More recent systems do have a behind-the-scenes “inner monologue” which enables them t
3917
GPT makes learning fun again
What will GPT unlock for the nerdy kid sitting in a 7th-grade classroom today?
3918
Replika AI: Your Money or Your Wife
Isn't there somebody you forgot to ask?
3919
Chatbots are not the future
Unfortunately for the countless hapless people I've talked to in the past few months, this was inexorable. Ever since ChatGPT exploded in popularity, my inner designer has been bursting at the seams.
3920
We aren't close to creating a rapidly self-improving AI
The current paradigm will not lead to an overnight superintelligence explosion.
3921
Study: ChatGPT outperforms physicians in quality, empathetic answers to patients
A new study published in JAMA Internal Medicine compared written responses from physicians with those from ChatGPT to real-world health questions. A panel of licensed healthcare professionals preferred ChatGPT’s responses 79% of the time.
3922
Stability AI releases DeepFloyd IF, a powerful text-to-image model
DeepFloyd IF is a state-of-the-art text-to-image model released on a non-commercial, research-permissible license that allows research labs to examine and experiment with advanced text-to-image generation approaches. In line with other Stability AI models, Stability AI intends to release a DeepFloyd
3923
3924
The State of Serverless GPUs
Comprehensive guide to understand the Serverless GPU Inference landscape.
3925
3926
Hidet: A Deep Learning Compiler for Efficient Model Serving
Hidet is a powerful deep learning compiler that simplifies the process of implementing high-performing deep learning operators on modern accelerators (e.g., NVIDIA GPUs). With the new feature of torch.compile(...) in PyTorch 2.0, integrating...
3927
3928
Year of the Voice – Chapter 2: Let's talk
Talk to your smart home and let it talk back with our new voice assistant features.
3929
Current architectural best practices for LLM applications
In this guide, I will share the standard architecture for data-informed language model applications and explain forthcoming improvements in knowledge retrieval.
3930
The future of programming: Research at CHI 2023
Research on programming tools published at CHI 2023.