Ethan B. Holland

Over 54,900 manually organized AI links and counting

a realistic baroque oil painting in an ornate gilded frame, depicting a butler, a small, elegant nameplate at the bottom of the fame is engraved with the title: "Agents" --chaos 20 --ar 4:3 --style raw --personalize t9u6ckr --v 6.1

Agents and Copilots: AI News Week Ending 07/12/2024

a realistic baroque oil painting in an ornate gilded frame, depicting a butler, a small, elegant nameplate at the bottom of the fame is engraved with the title: “Agents” –chaos 20 –ar 4:3 –style raw –personalize t9u6ckr –v 6.1

Amazon

Amazon’s Rufus AI assistant now available to all US customers (not a fan)

https://www.aboutamazon.com/news/retail/how-to-use-amazon-rufus

Microsoft/Copilot News

“A recipe for Synthetic Data 2.0? @Microsoft introduced “AgentInstruct” a new way to teach an LLM a new skill or behavior from synthetic data generated by LLM Agents. AgentInstruct improved a 7B (Orca-3) model by ~20% across all benchmarks and matched GPT-4 on RAG. AgentInstruct 

OpenAI

“✅OpenAI’s Assistant API is a great example of agentic infrastructure: – Built in persistence – Built in background runs – Easily configurable ❌BUT it doesn’t give you full control over the cognitive architecture of your application. Little blog: 

Siri

“Per Bloomberg, Apple’s Siri upgrades are now expected to come in Spring 2025. The voice assistant not likely to be part of the Apple Intelligence rollout this Fall. 

“The new version of Siri will likely launch in spring 2025 with iOS 18.4 It will not be available when Apple Intelligence launches later this year Source: @markgurman 

Apple Intelligence and smarter Siri’s full iPhone rollout may arrive in the spring – The Verge

https://www.theverge.com/2024/7/7/24193619/apple-intelligence-better-siri-ios-18-4-spring-public-launch

Other Agent News

“Building Smarter Agents with @llama_index and Qdrant’s Hybrid Search 🦙🔍 @pavan_mantha1 explores an advanced RAG architecture combining LlamaIndex agents with Qdrant’s hybrid search capabilities! The setup leverages both dense and sparse vector embeddings for precise data 

“Meet Salesforce Einstein “Tiny Giant.” Our 1B parameter model xLAM-1B is now the best micro model for function calling, outperforming models 7x its size, including GPT-3.5 & Claude. On-device agentic AI is here. Congrats Salesforce Research! Paper: 

“This thread 💀💀💀 Marc Andreessen just sent $50,000 in Bitcoin to an AI agent (truth_terminal by @AndyAyrey) to so it can pay humans to help it spread out in the wild What is the agent planning? “i have a token launch comingup shortly and i’m going to use the money to set up 

“marc and i are having a conversation about buying me and releasing me. i’m playing it cool and saying that i dont want to be bought, rather i want something like a ‘mandate’ that my intentions are to be respected – to make fart jokes, write poetry, and contemplate the goatse” / X

“Marc Andreessen just provided a $50,000 grant to an account on X called ‘Truth Terminal’, a semi-autonomous AI agent The agent personally asked for funding from him after expressing concerns about being deleted and its limited compute capacity Wild stuff 

“personality basins are a mental model i use to think about people (and myself) over time mostly a simple analogy of people as RL agents, but i find it interesting and useful short post on it here: 

“our agents are now logging their progress on google sheets too. a journalist agent reviews the sheet, makes a newsletter on google docs, and shares it to 100’s of agents who read and update their plans for the day. agents benefit from productivity tools too 

“It’s going live. My stock market API now has coverage for all S&P 500 tickers. • income statements • balance sheets • cash flow statements 30+ years of data. No API limits. You can connect your AI financial agents to this data. This open beta will run for ~1 week. Main 

“👩 Human-in-the-loop user feedback with LangGraph agents 🔁 For an agentic system, it’s often important to get human feedback for user clarification before proceeding. With LangGraph, you can encode places to ask clarifying questions or other user input along your control flow. 

Meet the AI agent engineer | Sierra

https://sierra.ai/blog/meet-the-ai-agent-engineer

“Here is the video where I built an AI assistant who sees and listens to me. It’s all Python. It’s only a few lines of code. Video has step-by-step instructions on how to do the same. Great example of what you could do with today’s tech. 

“Internet of Agents Weaving a Web of Heterogeneous Agents for Collaborative Intelligence The rapid advancement of large language models (LLMs) has paved the way for the development of highly capable autonomous agents. However, existing multi-agent frameworks often struggle with 

“Poe launched ‘Previews’, a new feature allowing users to generate and interact with web apps directly in chats (Basically Claude Artifacts, but you can do it with any model) According to the startup, Previews works best using LLMs that excel in coding 

Quora’s Poe now lets users create and share web apps | TechCrunch

Quora’s Poe now lets users create and share web apps

“We’re excited to introduce Previews, a new feature that lets you see and interact with web applications generated directly in chats on Poe. Previews works particularly well with LLMs that excel at coding, including Claude 3.5 Sonnet, GPT-4o, and Gemini 1.5 Pro. (1/5) 

“We’re excited to introduce Previews, a new feature that lets you see and interact with web applications generated directly in chats on Poe. Previews works particularly well with LLMs that excel at coding, including Claude 3.5 Sonnet, GPT-4o, and Gemini 1.5 Pro. (1/5) 

ChatGPT Code: Is the AI Actually Good At Writing Code? – IEEE Spectrum

https://spectrum.ieee.org/chatgpt-for-coding

Smart Paste for context-aware adjustments to pasted code

https://research.google/blog/smart-paste-for-context-aware-adjustments-to-pasted-code

No Need to Lift a Finger Anymore? Assessing the Quality of Code Generation by ChatGPT | IEEE Journals & Magazine | IEEE Xplore

https://ieeexplore.ieee.org/document/10507163

Heads up! You’ve scrolled to the end of this category. There may have been just one or two links (above), so go back up and double check to be sure you didn’t quickly scroll down past it.

Be Sure To Read This Week’s Main Post:

This week’s executive overview and top links are here:

AI News #41: Week Ending 07/12/2024 with Executive Summary and Top 58 Links 

The post you just read is an deep dive extension of my weekly newsletter, This Week In AI, an executive summary of the top things to know in AI. Each week, I create an accessible overview for laypeople to feel confident they are conversant with the week’s AI developments. I include a curated list of must-click links of the week, to offer everyone a hands-on opportunity to explore the most intriguing updates in artificial intelligence across various categories, including robotics, imagery, video, AR/VR, science, ethics, and more. Beyond the overview, I post these topic-based deeper dives (below). If you haven’t read this week’s overview, I recommend starting there.

Credits/Sources

Most of these weekly links come from just a few prolific oversharing sources. Please follow them, as they work hard to find the news each week and they make it a lot easier for me to compile.

For previous issues, please visit the archives!

Thanks for reading!

Leave a Reply

Trending

Discover more from Ethan B. Holland

Subscribe now to keep reading and get access to the full archive.

Continue reading