Flux[dev]: A futuristic robot, sleek smooth humanoid design. Smooth, glossy black faceplate with no visible facial features, high-tech, minimalist appearance. The robot’s body is matte black or dark gray, with articulated joints and mechanical parts that resemble those of a human, including fingers. In the background is a secret headquarters. It’s a dramatic scene. Across the front of the image, the word “Agents” is written in cool spy text.
LangChain
“🤝Integrating human input: How agents can ask for help when needed Sometimes agents running in the background need information from the user. How can they reach out to a human to get that info? We discuss this UX in our recent blog on ambient agents
“🔑 Improved filtering for traces in LangSmith You can now filter traces or runs by JSON key-value pair in the inputs or outputs. This makes filtering more precise so you can find exactly what you’re looking for, especially when working with structured data. You can also match
“🐶Denser Retriever An enterprise-grade AI retriever designed to streamline AI integration into your applications Blends keyword based search, vector retrieval, and rerankers 🦜Uses the document loaders and text splitters from LangChain!
OpenAI
“Long awaited, but finally – Structured Outputs. gpt-4o-2024-08-06 achieves 100% reliability in our evals, perfectly matching the output schemas. 🔥 Super useful for downstream task, when the model is not calling a tool, but rather, responding to the user in a structured way. A
Inside Turing, the company gathering ‘human data’ for every major AI company | Semafor
“Guaranteed valid tool calls from OpenAI Tool calling is incredibly useful for building LLM-steered applications. One of the key difficulties with tool calling is getting models to reliably generate arguments that respect the tool schema. Earlier today OpenAI announced that you
“Structured output is all you need! Structured outputs can help to improve the performance and reliability of your LLM application. OpenAI just announced that they are now supporting structured outputs in the API. You can use it with function calling and defining your own
Introducing Structured Outputs in the API | OpenAI
OpenAI: Introducing Structured Outputs in the API
“On one hand, OpenAI just made it so that its models can be forced to output in JSON, which makes it much easier for developers to use LLMs in their programs. On the other hand, forcing LLMs to answer in JSON lowers their reasoning ability (but helps classification)” / X
“It went under the radar but OpenAI released their most performant GPT-4o assistant model yesterday. – Structured outputs with 100% reliability – 4x max token (16,384) output limit – 50% cheaper on inputs – 33% cheaper on outputs – #1 on the @allen_ai ‘s ZeroEval leaderboard
Siri
“Apple is once again rumored to charge $10-20/month for its advanced Apple Intelligence features (via CNBC). Would you pay for Apple Intelligence?
Other Agent News
“Today we’re rolling out a new way to build automation with Bardeen’s AI agent. It’s the next evolution of automation platforms that’s both flexible and reliable.
NVIDIA AI Developer on X: “Meet James, an interactive digital human knowledgeable about our products. Talk to James ➡️ https://t.co/YXoT6fRD8t 💬 James uses a collection of NVIDIA and @elevenlabsio digital human technologies to provide natural and immersive responses. https://t.co/53IfOg0w8O” / X – https://twitter.com/NVIDIAAIDev/status/1821637513728950441
Humane’s daily returns are outpacing sales – The Verge
“Mixture of Agents (MoA) — a framework that leverages the collective strengths of multiple LLMs. Each layer contains multiple agents that refine responses using outputs from the preceding layer. 👨🔧 Mixture of Agents is an advanced technique in AI that combines multiple models to
“We continue to be excited about Workflows, our new abstraction for building complex agentic gen AI applications! To demonstrate how easy it is to handle real workflows, in our latest video, we show you how to rebuild LlamaIndex’s built-in Sub-Question Query Engine using our new
“Introducing @MistralAI agents! You can now build your agents based on Mistral models or fine-tuned models and use on Le Chat 🙌 More features coming soon!
“Composio (@composiohq) is a cool production-ready toolset for AI agents 🛠️ – it includes 100+ tools including Github, Slack, Salesforce, and more. We are eager to feature tutorial by the Composio team on how to build a PR review agent using Composio Github/Slack tools and
“Nice survey paper on current practices and solutions for LLM-based agents for software engineering. Covers important topics such as requirement engineering, code generation, test generation, and autonomous decision making. It also includes benchmarks, metrics, and models used
“Announcing Einstein Copilot in Slack 🧑🏼✈️, your conversational interface for collaborating with human & digital coworkers. Unlock all the knowledge and public channel conversations in your company to make everyone an Einstein✨ ▶ Takes action and gives quick answers where you
“Could AI agents develop a language incomprehensible to humans?💬 Our CEO @ronbodkin discusses decentralizing AI for transparency at @BerkeleyRDI’s panel during @StanfordCrypto’s Blockchain Week. 🔍 With:
“Introducing @MistralAI agents! You can now build your agents based on Mistral models or fine-tuned models and use on Le Chat 🙌 More features coming soon!https://twitter.com/sophiamyang/status/1821476909345128740
Leave a Reply