Same prompt, same retrieved congressional content. One generation from Meta-Llama-3.1-8B-Instruct-Turbo (together.ai), the other from gpt-4o-mini. Both less than one penny in inference costs. I had to add more decimal places to the cost display :) "Create a table identifying the main challenges in keeping social security funded. Create the following columns, * challenge: a specific challenge social security faces * solution: a proposed solution * legislation: legislation describing the challenge or the solution"
Gabriel Altay’s Post
More Relevant Posts
-
OpenAI's leverage over legacy media is on full display: WaPo, which is bleeding out, has little choice but to turn over its data in exchange for the hope that OpenAI can save it. This as NewsCorp signs a historic deal to turn over data from all their properties (WSJ, NYpost, Times/Sunday Times, and more). No matter how you slice it, a new paradigm of journalism is here. Time will tell... https://lnkd.in/eJHa8u6k https://lnkd.in/erG-hUK2 #OpenAI #AI #GenAI
-
Director of Business Development at The Lynx Group | Customer Loyalty | Nonprofit Advocacy
"The probability that advanced A.I. will destroy or catastrophically harm humanity is 70 percent... The world isn’t ready, and we aren’t ready, and I’m concerned we are rushing forward regardless and rationalizing our actions" A bit frightened by these statements made by Daniel Kokotajlo, a former researcher at OpenAI's governance department. Pursuing profits over safety is an age-old story in the corporate world; and the fallout of a lack of ethical behaviour is more dangerous than ever here. None of us know what's going on inside these companies, and that's why employees being able to freely express concerns and criticism is so important. I hope to see new operational processes enabling open dialogue to be put in place because these reports are... troubling, to say the least. Great read for anyone interested in AI and corporate governance: https://lnkd.in/gs9hQerg
OpenAI Insiders Warn of a ‘Reckless’ Race for Dominance
https://www.nytimes.com
-
When working with LLM, one of the major issues is having false or incomplete answers. This is called hallucination. Resolving these issues will be difficult because of the undeterministic nature of LLMs. In this article, researchers propose a way to reduce these issues. You can read the original paper at this https://lnkd.in/eSyNyFPk or read the summary from DeepLearning.AI at this https://lnkd.in/ekNEkgcJ.
Hallucination Detector, Battle of the Image Generators, and more
deeplearning.ai
-
"Faced with the chaotic, messy reality of everyday life, LLMs are useful tools for summarizing text, fetching information, understanding data, and creating structure. But always, always with human oversight: guiding the summaries and then checking the results, teaching the bot to navigate an audit report, deciding when and when not to put the bot in control, and designing the rest of the software that powers the site." A great summary by Zach Seward on the current state of AI in journalism. https://lnkd.in/eVzyjx8w
AI news that's fit to print
zachseward.com
-
In this overview, Cameron R. Wolfe, Ph.D. shows the basic components of AI-powered search systems, including lexical search, bi-encoders, and cross-encoders:
The Basics of AI-Powered (Vector) Search
towardsdatascience.com
-
Helping CIOs and IT leaders make strategic, timely, and well-informed decisions 📈📊/ Fitness Fanatic 🏋️♂️🏃♂️/ Avid Reader 📚
Discover Info-Tech Research Group's March 2024 AI Transformation Briefing which covers recent news from major LLM providers, including OpenAI, Google, AWS, Anthropic, and Mistral. Download the latest research here 👉 https://lnkd.in/gWe8jYFq #AI #ArtificialIntelligence #TransformationBriefing #AIWorkshops
AI Transformation Brief – March 2024
infotech.com
-
Discover Info-Tech Research Group's March 2024 AI Transformation Briefing which covers recent news from major LLM providers, including OpenAI, Google, AWS, Anthropic, and Mistral. Download the latest research here 👉 https://lnkd.in/gWe8jYFq #AI #ArtificialIntelligence #TransformationBriefing #AIWorkshops
AI Transformation Brief – March 2024
infotech.com
-
Discover Info-Tech Research Group's March 2024 AI Transformation Briefing which covers recent news from major LLM providers, including OpenAI, Google, AWS, Anthropic, and Mistral. Download the latest research here 👉 https://lnkd.in/gWe8jYFq #AI #ArtificialIntelligence #TransformationBriefing #AIWorkshops
AI Transformation Brief – March 2024
infotech.com
-
Discover Info-Tech Research Group's March 2024 AI Transformation Briefing which covers recent news from major LLM providers, including OpenAI, Google, AWS, Anthropic, and Mistral. Download the latest research here 👉 https://lnkd.in/gWe8jYFq #AI #ArtificialIntelligence #TransformationBriefing #AIWorkshops
AI Transformation Brief – March 2024
infotech.com
-
Senior Regional Director @ Info-Tech | Master's in Entrepreneurship, Technology and Innovation Management
Discover Info-Tech Research Group's March 2024 AI Transformation Briefing which covers recent news from major LLM providers, including OpenAI, Google, AWS, Anthropic, and Mistral. Download the latest research here 👉 https://lnkd.in/gWe8jYFq #AI #ArtificialIntelligence #TransformationBriefing #AIWorkshops
AI Transformation Brief – March 2024
infotech.com
ML @ Tempus AI | formerly Kensho | CMU PhD Computational Physics
4moUsing Llama 3.1 70B, you just might be able to break the $0.01 barrier :)