Annotated talk slides by Arvind Narayanan and Sayash Kapoor of Princeton University, dated October 4, 2023, on evaluating large language models. The slides discuss three hard problems in LLM evaluation: prompt sensitivity, construct validity and contamination, and examine questions about ChatGPT's behavior over time and its political bias.
Directory
Search results
Published directory entries matching your search.
AITV is the world's first AI streamer factory - built for creators, brands, and communities.
A blog post by Hamel Husain, published February 14, 2024, describing how to intercept LLM API calls with mitmproxy to see the prompts sent by frameworks such as Guardrails, Guidance and Langchain. The post argues that these prompts are the fastest way to understand how such tools work.
Falcon LLM is described as a generative large language model that supports applications and use cases. The site presents models in the Falcon LLM family, including Falcon-H1 and Falcon-E, and lists Falcon-H1 model insights. It also references Falcon Arabic for Modern Standard Arabic and dialects, and names Falcon-Emirati, Falcon-ASR and Falcon-OCR-Arabic.
FastAgency is an open-source AI development tool designed to build and scale multi-agent workflows for production use. It provides modular, integrable agents to accelerate the development of complex AI solutions.
Fiber is a Python-based distributed computing library for modern computer clusters. It provides the same API as Python's standard multiprocessing library, uses Nanomsg for communication, and allows dynamic allocation of CPU, memory, and GPU resources. Installation uses pip install fiber.
Fiddler is an AI control plane platform for enterprise AI agent deployments. It offers evaluation, monitoring, policy enforcement, governance, and cost efficiency functionality for enterprise AI systems. The platform supports use cases across government, financial services, healthcare, and insurance sectors.
Figure is the first-of-its-kind AI robotics company bringing a general purpose humanoid to life.
FigureLabs is an AI scientific figure generator that creates illustrations, flowcharts and plots. It accepts text, sketches, lab photos, spreadsheets, PDFs or reference figures as input, then allows editing of text, colors, backgrounds and resolution on a canvas. Figures can be exported as editable PPTX or SVG, or as PNG and JPG images.
Using AI, FinChat generates answers to questions about public companies and investors.
Documentation for Fine Tuning Guide, covering setup, features, and practical usage.
Flyflow is a GitHub organization with public repositories including an OpenAPI specification for the Flyflow API, a service framework, a Python library, and demo applications and notebooks. The organization page lists no public members.
FoLiA is an XML-based format for linguistic annotation intended for representing and exchanging written language resources such as corpora. It aims to accommodate many annotation types through a generalized paradigm without committing to a particular label set, language or linguistic theory. The project includes documentation, a RelaxNG schema and software libraries.
FontVibe is a free AI-powered font generator that creates custom text artwork. Users can either describe their desired style or select from over 120 available text effect styles, including neon, glitch, fire, and 3D options. Finished artwork can be downloaded instantly as PNG or JPG files.
Forefront is described as a platform to fine-tune and inference open-source language models. The site mentions building with open-source AI, fine-tuning models on data, and running inference through serverless API endpoints. It also describes storing training, validation and evaluation data in ready-to-fine-tune datasets. Pricing lists a free tier and a team plan at $99 per month, each including $20 in free credits.
This is the public GitHub profile of Devin Stein, which hosts 57 public code repositories for community access. Visitors can follow the profile to view and use Stein's shared code on the GitHub platform.
Free Ebooks Download Links is a blog that provides links for downloading e-books available freely in different formats. The books are published online by their authors for free viewing and printing for non-commercial purposes. Categories include artificial intelligence, machine learning, information theory and communication systems.
FULIR Data is a repository of research data and datasets with open access. The listing shows a recently added dataset of NMR spectra for a study on antibiotics, with each folder containing the NMR data of one sample and multiple spectra per sample.
FutureTools is a curated AI news and tools site by Matt Wolfe. It aggregates AI headlines, expert commentary, top tools, and interviews, and offers a newsletter described as having 250,000+ subscribers.
Telegram link is a Telegram channel, group, or bot link for updates, files, community posts, or support.
Creates, rewrites or summarizes written content with language models.
Creates, rewrites or summarizes written content with language models.
A curated UC Berkeley Law Library guide collecting resources on generative AI applications in law school, higher education, and legal practice. It links news, studies, ethics materials and access-to-justice research, and notes that the resources will be regularly updated.
The article 'Generative AI: A Creative New World' by Sequoia Capital discusses the emergence of a powerful new class of large language models that enable machines to write, code, draw, and create with credible or superhuman results. It contrasts analytical AI with creative AI.