Cadenza

Listen to an unedited interview between an amazing candidate and our AI interviewer. A great interviewer makes you feel comfortable, heard, and brings out the best in you. That's the kind of interviewer we're building with Recruit AI.

Mixture of Agents—a framework that leverages the collective strengths of multiple LLMs. Each layer contains multiple agents that refine responses using outputs from the preceding layer. Together MoA achieves a score of 65.1% on AlpacaEval 2.0. Together MoA uses six open source models as proposers and Qwen1.5-110B-Chat as the final aggregators with three layers. We also evaluate on FLASK which offers more fine-grained evaluation and outperforms original models on most of the dimensions. Both Together MoA and Together MoA-Lite are on the Pareto front, indicated by the dashed curve, in the performance vs. cost plot. Try Together MoA through our interactive demo. Please note that the TTFT is slow at the moment due to the iterative refinement process of MoA, but we are actively working on optimizations. 📣 Blog: https://lnkd.in/g26Ya_98 📄 Paper: https://lnkd.in/g_vc9Hac ⌨️ Code: https://lnkd.in/gF2xEEeb 🖥️ CLI Demo: https://gttps://https://lnkd.in/gifKtUQv This work was made possible through the collaborative efforts of several open-source projects. We appreciate Meta, Mistral AI, Microsoft, Alibaba Cloud, and Databricks for developing the Llama, Mixtral, WizardLM, Qwen, and DBRX models. We also thank Tatsu Labs, lmsys.org, and KAIST AI for the AlpacaEval, MT-Bench, and FLASK evaluation benchmarks.

𝐂𝐨𝐢𝐧𝐃𝐂𝐗 𝐥𝐚𝐮𝐧𝐜𝐡𝐞𝐬 𝐂𝐨𝐢𝐧𝐃𝐂𝐗 𝐏𝐫𝐢𝐦𝐞 𝐟𝐨𝐫 𝐇𝐍𝐈𝐬, 𝐅𝐚𝐦𝐢𝐥𝐲 𝐎𝐟𝐟𝐢𝐜𝐞𝐬 𝐚𝐧𝐝 𝐈𝐧𝐬𝐭𝐢𝐭𝐮𝐭𝐢𝐨𝐧𝐚𝐥 𝐈𝐧𝐯𝐞𝐬𝐭𝐨𝐫𝐬! CoinDCX has served over 1.5 crore customers and helped make #crypto more accessible to the masses. We wanted to expand further and recently introduced CoinDCX Prime to provide customised services, dedicated account managers, and structured products for High Value Investors . We are glad to already have the support and trust of 🏦 100 institutional investors 💼 2,500+ HNI clients 🏚️ 25 family offices It is amazing to see how crypto is becoming an important asset class that everyone is looking at!

We are excited to announce the launch of Dragonfly, an instruction-tuned vision-language architecture that enhances fine-grained visual understanding and reasoning about image regions! The Dragonfly architecture employs multi-resolution visual encoding and zoom-in patch selection to enhance multimodal reasoning while being context-efficient. We are also releasing two new open-source models: 1. Llama-3-8b-Dragonfly-v1: A general-domain model trained on 5.5 million image-instruction pairs, demonstrating promising performance on vision-language benchmarks like visual QA and image captioning. 2. Llama-3-8b-Dragonfly-Med-v1: A biomedical model fine-tuned on 1.4 million biomedical image-instruction pairs, in collaboration with James Zou's group at Stanford University School of Medicine. Dragonfly-Med outperforms prior models, including Med-Gemini, on multiple medical imaging tasks, showcasing its capabilities for high-resolution medical data. We hope this open-source release will benefit the research community in exploring multimodal AI applications and addressing real-world problems. Read more on our blog: https://lnkd.in/g3jDk34w Arxiv Paper: https://lnkd.in/gsbYk6mV Codebase for architecture implementation: https://lnkd.in/gsBk9n6P

With 7 figures of annualized revenue and another month of growth in the books, Affiniti is growing our team across all functions: — Capital Markets — Growth & Operations — Engineering We are looking for relentless individuals who want to go all in on something that can transform industries (yes - multiple) across America. Apply with the understanding that we are building an all or nothing business. Our full job board is here: https://lnkd.in/gUDCQMPH You can also send me a message if you're interested!

At Together AI we have an increasing number of customers and partners leveraging the Together API for multi-agent workflows and applications. The ability to leverage multiple models, with industry-leading performance has made Together Inference a leading solution for agent-based workflows. Recently we worked with Axiomic, a new AI agent build framework, who integrated the Together API into the core framework as the provider for using open-source models. In our most recent blog we explore agent building using one of Axiomic's demos called GEAR Chat, which shows how four agents work together to provide a portable, steerable, and debuggable chat agent. Read more here: https://lnkd.in/gsBPviiG

Argentina, líder en adopción crypto en América Latina 🌍 Marcelo Cavazzoli, Founder & CEO de Lemon, resaltó el crecimiento y la madurez del ecosistema crypto en Argentina en una nota de Criptotendencias 🙌 ¿Qué nos permite afirmar esto? 🔹 El interés y la confianza en el ecosistema están en aumento: 4 de cada 10 nuevos usuarios crypto en Latam son de Argentina 📈. 🔹 Promovemos el ecosistema crypto y las startups argentinas como un hub de innovación 🌱. 🔹 Argentina está en camino a convertirse en la capital mundial crypto 🚀. Seguimos liderando la revolución. Leé la nota completa acá 👉 https://lnkd.in/dqyAPSkm

Recruit AI is live on Product Hunt 🎉 𝗣𝗹𝗲𝗮𝘀𝗲 𝘀𝘂𝗽𝗽𝗼𝗿𝘁 𝘂𝘀 𝘁𝗼𝗱𝗮𝘆 - https://lnkd.in/gzAT64-w Thank you for being part of our community and for your continued enthusiasm.

Exciting news! Over the last 2 months the team at Ribbon has been hard at work building the first-of-its-kind AI interviewer, Recruit AI. It's natural-sounding and able to ask intelligent questions. To put Recruit AI through its paces we've interviewed 1000+ candidates by working with early partners. Today we're announcing general availability of Recruit AI and launching on Product Hunt. Please help support us on Product Hunt! (LIC).

We are excited to be working closely with the i2c Inc. team to help small business owners across the nation 10X their financial operations! This is just the tip of this iceberg of an opportunity. Our team at Affiniti is shipping new product every single week to meet our customers' needs & demands. Onwards! https://lnkd.in/gmnXhtif