Generative AI Model Updates and Trends

Based on over 1,100 curated papers and announcements featured throughout the year - the AI Tidbits SOTA report for 2023 is out. Just before we yell at ChatGPT once again as it got one detail wrong, let’s review the state-of-the-art today compared to December 2022 across various generative AI verticals. https://lnkd.in/gkBykSdS Here's a glimpse from the report: (1) Language models - within a year, the open-source community welcomed models like Yi and Mistral's Mixture of Experts that outperformed GPT-3.5. Meanwhile, commercial models like GPT-4 and Claude 2.1 continued to push the boundaries of language understanding, achieving exceptional scores in medical and bar exams and placing them among the top percentile. (2) Multimodal AI - 2023 was a stellar year with models like CogVLM, LLaVA, and GPT-4V(ision) demonstrating an unparalleled ability to process and interpret multiple forms of data, bringing us closer to AI that mimics human sensory inputs. (3) Autonomous agents - we saw groundbreaking progress in autonomous agents frameworks like AutoGPT and open-source models like CogAgent, signaling a near future where AI companions are an integral part of our everyday lives. (4) Image generation - it’s hard to believe that image diffusion models as we know them are less than two years old. DALL-E 3 and Midjourney led the pack in 2023, elevating the art of image synthesis and making it more accessible through ChatGPT and packages like Fooocus. No more deformed hands and faces or non-readable text. That’s 2022. (5) Video generation - Pika Labs and Runway were at the forefront with their foundation models, significantly improving video duration and quality in 2023. Meta's release of Emu Video and open-source projects like VideoCrafter1 also made notable contributions to this rapidly evolving space. (6) Speech understanding and generation - OpenAI’s Whisper and Deepgram’s Nova-2 showcased remarkable improvements in transcription accuracy, while ElevenLabs' text-to-speech model blurred the line between AI-generated and human voices, supporting input streaming for real-time speech synthesis. (7) Music generation - Meta’s MusicGen and Suno AI transformed text and melodies into music, marking a new era in AI-powered customized music creation. 2023 was a year where generative AI not only matched but, in many cases, surpassed human capabilities across various modalities. The open-source community particularly shined, boasting nearly 1,000 models on Hugging Face's Open LLM Leaderboard. 2024 could be the year in which an open-source model (powered by Mistral's next release?) surpasses GPT, AI companions become part of our daily lives through on-device small language models, and people no longer believe what they cannot physically touch. For a deep dive into these developments and a comparison between the state-of-the-art in 2022 and 2023, check out the full AI Tidbits 2023 SOTA Report https://lnkd.in/gkBykSdS

In the two years since ChatGPT's release catalyzed generative AI's Cambrian explosion, enterprise spend in the category has surged to $13.8 billion -- up more than 6x from $2.3 billion last year. In Menlo Ventures' 2024 State of Generative AI Report, my partners Tim Tully, Joff Redfern, and I surveyed 600 enterprise IT decision-makers to document the scope and scale of the transformation. Our second annual report found that: 1/ Generative AI has found screaming product-market fit in its first few breakout use cases: 🥇 Code copilots (51% adoption) - e.g., All Hands AI, Codeium, Harness 🥈 Support chatbots (31%) - e.g., Aisera, Decagon, Sierra 🥉 Enterprise search (28%) - e.g., Glean, Sana 2/ The foundation model landscape is shifting: Buoyed by the release of state-of-the-art models like Claude Opus, Sonnet, and Haiku, Anthropic doubled its enterprise share from 12% to 24% while OpenAI slipped from 50% to 34%. Closed-source models remained dominant vs open-source models (e.g., Llama) with 81% market share. 3/ Whatever your department, there's an app for that. Generative AI budgets are coming from every part of the organization: 🤝 Sales - Clay, Unify 📢 Marketing - Typeface, OfferFit 👔 HR - ConverzAI 💵 Accounting & finance - Numeric 4/ Vertical AI applications are especially gaining momentum. Companies like Abridge in healthcare and Casetext, Part of Thomson Reuters and Harvey in legal have already become the talk of the industry. The leading adopters today are: ⚕ Healthcare - $500M in genAI spend ⚖ Legal - $350M 🏦 Financial services - $100M 📽 Media & entertainment - $100M 5/ In the modern AI stack, RAG (retrieval-augmented generation) has dethroned simple prompting as the primary design pattern for AI apps, powering 51% of implementations (up from 31% last year) and driving the adoption of key infrastructure building blocks like Pinecone, unstructured.io, and Neon. Meanwhile, agentic designs are just emerging, already driving 12% of deployments. All this and more in our full report. Check it out: https://lnkd.in/gByCqFMB

As generative AI shifts from pilot to production, efficiency, cost, and scalability matter a lot more. Founded 2 years ago as "AWS for Generative AI," Together AI has raised $240M to provide cloud compute optimized for AI workloads. In this week's episode of my #AskMoreOfAI podcast, CEO/founder Vipul Ved Prakash talks about innovations to make models faster and smarter including: 🔹 FlashAttention: Smart GPU-aware tricks to reduce memory needed for calculating attention and rearrange calculations to speed up inference. 🔹 Speculative decoding: Speeds up inference by predicting multiple tokens in advance instead of one at a time, then selects the best ones and prunes the rest. 🔹 Model quantization: Reduce model size and speed up inference by reducing precision of numerical representations used in models without significantly degrading performance. In most LLMs, parameters are stored as 32-bit floating-point numbers, which consume a lot of memory and processing power. Quantization converts these to lower sig figs, eg 16-bit floats or even 8-bit integers.   🔹 Mixture of Agents, combining use of multiple specialized models (agents) that work together, with each agent handling a different aspect of a problem such as a sales agent, sales manager agent, deal desk agent, and legal contracts agents collaborating together. Vipul predicts that cloud compute for #GenAI will surpass the traditional hyperscaler business within 2-3 years. Salesforce Ventures is proud to have led the Series A earlier this year, and customers running models on Together can BYOM with Einstein Model Builder. 🎧 Listen or watch here! https://lnkd.in/g6XX4KCR

From chatbots to code generation, and from creative design to personalized automation, Gen AI is transforming how machines understand, reason, and create. Generative AI is not just a buzzword anymore, it’s the engine driving innovation across industries. Here’s the break down 👇 Core Concepts - Gen AI runs on foundation models like GPT and Gemini that learn from massive datasets. - Concepts like Prompt Engineering, RAG, and Chain-of-Thought help AI think and plan effectively. - Techniques like Few-Shot, Zero-Shot, and Multi-Modal Learning enhance flexibility and cross-domain intelligence. How It Works - Gen AI uses Transformers and attention mechanisms to understand and generate context-aware output. - It relies on embeddings, sequence modeling, and RLHF to refine responses through feedback and learning. Applications - From text generation and AI chatbots to code writing and content creation, Gen AI boosts productivity and creativity everywhere. - It’s also revolutionizing design, education, and automation with intelligent, adaptive solutions. Challenges - Despite its power, Gen AI faces issues like bias, hallucination, and data privacy risks. - Scalability, context limits, and ethical use remain ongoing challenges for developers and businesses. The Future - Gen AI is evolving into Agentic AI, systems that can plan, reason, and collaborate independently. - Expect smarter models with memory, context awareness, and autonomous decision-making in the near future. Popular Tools - Top platforms include OpenAI, Anthropic Claude, Google Gemini, Meta LLaMA, and Mistral AI - Frameworks like LangChain, Hugging Face, and Stability AI simplify Gen AI development. In short: Gen AI bridges automation and intelligence - combining creativity, logic, and adaptability to shape a smarter future. #GenAI

The fourth edition of my AI Trends report is out. I've been writing these since 2022 (before ChatGPT launched), and this year's is the most comprehensive yet—100+ pages covering adoption data, labor market shifts, energy constraints, and a market map of 1,800+ AI startups. The short version: generative AI has crossed the chasm. The data's pretty clear on that now. Full report and summary here: https://lnkd.in/gXzrNvD3 Also attaching a preview of the first section of the report.

🌟 The Generative AI Landscape: Shifting from 2024 to 2025 🌟 As we step into 2025, the generative AI landscape is undergoing a significant transformation, and here are some key trends we're witnessing: ✨ From Hype to Practical Impact ✨ The initial excitement around generative AI has evolved into a more pragmatic approach. Companies are now focusing on delivering tangible business outcomes, enhancing data quality, and developing talent to harness the full potential of AI. 🎯 Delivering Tangible Business Outcomes: AI is being used to solve real-world problems, such as optimizing supply chains, enhancing customer experiences, and improving operational efficiencies. 🔍 Enhancing Data Quality: High-quality data is crucial for AI success. Organizations are investing in data governance and management to ensure their AI models are trained on accurate and relevant data. 🚀 Rise of Small Language Models (SLMs) 🚀 SLMs require less computational power, making them more affordable for businesses, and they offer better accuracy and relevance for specialized industries such as retail, healthcare, finance, and legal services. 🔗 Integration and Governance 🔗 Organizations are adopting new technologies and architectures to better govern data and AI. This includes a return to predictive AI for over 50% of use cases, leveraging historical data to forecast future events or behaviors. Robust data governance frameworks are also being implemented to ensure data privacy, security, and compliance with regulations. 🤖 Agentic AI 🤖 Agentic AI represents the next frontier of AI. These systems use sophisticated reasoning and iterative planning to autonomously solve complex, multi-step problems. With the ability to adapt to new information and changing conditions, agentic AI is set to enhance productivity and operations across various industries, from supply chain optimization and cybersecurity vulnerability analysis to assisting doctors with time-consuming tasks. 🎥 Video Analysis Use Cases 🎥 The landscape of video analysis is expanding rapidly, presenting exciting use cases across industries. AI can help auditors identify pirated media online, significantly speeding up the manual process and improving accuracy. Furthermore, AI-generated videos, video podcasting, and AI voices and avatars for training videos are shaping the future of video content creation, providing a more engaging and interactive experience. In 2025, my focus will be on creating content that explores industry-specific use cases and implementation strategies for AI. I will dive deep into these topics, providing insights, best practices, and real-world examples to help businesses leverage AI effectively. Stay tuned for in-depth articles, case studies, and practical guides that will help you navigate the evolving AI landscape. Follow me to stay updated and join the conversation! #GenerativeAI #AI2025 #Innovation #Technology #FutureOfAI