Microsoft's LangChain alternative: Guidance
Plus: Google Cloud launches AI tools for drug discovery. Tesla and Sanctuary AI reveal the AI Humanoid Robots.
Hello, Engineering Leaders and AI Enthusiasts,
Welcome to the 21st edition of The AI Edge newsletter. In today’s edition, we bring you Microsoft's LangChain alternative: Guidance. Thank you everyone who is reading this. 😊
In today’s edition:
🗺️ Microsoft's LangChain alternative: Guidance
💊 Google Cloud launches AI tools for drug discovery & precision medicine
🤖 The arrival of AI Robots: Sanctuary AI's Phoenix and Tesla Bot
📚 Using Large Language Models Effectively by
Let’s go!
Microsoft releases Guidance language for controlling large language models
Microsoft has released a new guidance language for controlling large language models (LLMs) that allows developers to interleave generation, prompting, and logical control into a continuous flow, which can significantly improve performance and accuracy.
The tool features simple and intuitive syntax, rich output structure, support for role-based chat models, easy integration with HuggingFace models, and intelligent seed-based generation caching. It also offers playground-like streaming in Jupyter/VSCode notebooks and regex pattern guides to enforce formats.
Why does this matter?
The release of guidance offers more effective ways of working with language models and could play an important role in advancing the development and adoption of AI technologies. Moreover, seems like Microsoft has finally decided to test open-source waters in case of AI developments.
Google Cloud launches AI tools for drug discovery and precision medicine
Google Cloud has launched two AI-powered tools to help biotech and pharmaceutical companies accelerate drug discovery and advance precision medicine. The Target and Lead Identification Suite aims to streamline the process of identifying a biological target and predicting protein structures, while the Multiomics Suite assists researchers in ingesting, storing, analyzing, and sharing large amounts of genomic data. Both tools aim to significantly reduce the time and cost associated with drug development.
Several companies, including Pfizer, Cerevel Therapeutics, and Colossal Biosciences, have already been using these products. Cerevel Therapeutics estimates that it will save at least three years on average by using the Target and Lead Identification Suite to discover new drugs.
Why does this matter?
AI seems to benefit humanity the most through its use in medicine and diagnostics. This launch from Google and the subsequent adoption by a pharma giant like Pfizer indicate the swift mainstreaming of the tech.
The arrival of AI Robots: Sanctuary AI's Phoenix and Tesla Bot
Sanctuary AI has unveiled a new humanoid robot named "Phoenix," designed for general-purpose work.
The robot has advanced sensors and control systems allow it to move and interact. It is still in the early stages of development and will require further testing and refinement before it can be used commercially. However, it is expected to have a range of potential applications.
Specifications:
Height: 5'7"
Weight: 155 lbs
Can lift to 55 pounds
Can move at speeds of up to 3 miles per hour
Tesla’s Tesla Bot also has a present mark here, It’s also designed to perform repetitive tasks such as lifting heavy objects or working in hazardous environments and is intended to be a general-purpose robot for various industries.
Moreover, Engineers at the University of Waterloo have created a prototype of a companion robot capable of assisting people with dementia in locating misplaced objects. The robot uses an object-detection algorithm and camera to keep track of specific objects in its view, recording the time and date of entry and exit.
Why does this matter?
Multiple players entering the robotics market could have significant implications for the industry, like manufacturing, logistics, healthcare, etc. This technology could improve the quality of life for individuals and reduce the burden on caregivers.
Knowledge Nugget: Using Large Language Models Effectively
This insightful share from
and boils down the lessons learnt by early adopters of LLMs.The 8 key lessons shared are:
Engage users in co-creation
Start with lower-stakes tasks
Add additional trust and safety layers
Leverage embeddings
Feed models more context
Augment these models’ power with new tools
Use hybrid approaches
Have larger models train smaller models
Why does this matter?
The AI landscape is evolving at a rapid speed, making it difficult for leaders to decipher the right implementation plan. However, the lessons shared here draw a fundamental roadmap to leverage LLMs. Since most lessons fall back to the fundamentals, the roadmap remains unaffected by the quick-moving technological advancements.
What Else Is Happening
🤖 Sam Altman, OpenAI chief, openly discusses AI dangers during his interview with senators. (Link)
💬 Zoom to integrate Google-back Anthropic’s chatbot following the OpenAI partnership. (Link)
⛽ AI will help Shell find oil in the deep sea. (Link)
📊 StructGPT shares methods to improve zero-shot reasoning ability of models over structured data. (Link)
🔄 Symbol tuning uses input-label mappings to improve robustness to prompts without instructions. (Link)
Trending Tools
Superflows: AI email assistant for faster inbox management with AI summaries, 1-click replies and custom tone of voice.
dora AI: Generate powerful websites with a single prompt using AI 3D animation.
MyShell: Innovative chatbot platform with virtual beings having unique personalities & voices.
Nack AI: Chat with AI and generate amazing images on iPhone and Android.
Feathery AI: Create high-quality forms in seconds and customize with our powerful editor.
Ari: Chrome extension for using AI from any online text box to improve writing, research, coding or get advice.
Iconify: Let AI design the perfect app icon in seconds. Trusted by 700+ customers.
CaseIt: Automatically generate test cases in any programming language using AI.
That's all for now!
If you are new to ‘The AI Edge’ newsletter. Subscribe to receive the ‘Ultimate AI tools and ChatGPT Prompt guide’ specifically designed for Engineering Leaders and AI enthusiasts.
Thanks for reading, and see you tomorrow.