Generating Human-level Text with Contrastive Search in Transformers đ¤
Weâre on a journey to advance and democratize artificial intelligence through open source and open science.
More from the blog
Reinforcing the value of human understanding at MIT
During the School of Humanities, Arts, and Social Sciencesâ 75th Anniversary Symposium, President Sally Kornbluth said âMIT has never needed your particular insight and guidance more than we do now.â
Bringing foundational models to the front lines of TB screening
Generative AI
Q&A: How AI came to model the âmessyâ human mind
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
This design software reimagines everyday objects as self-aware devices
âX-Hingesâ helps design and 3D print items like lamps and gloves with an interactive twist: automatically embedded sensors that perceive and adaptively respond to human contact.
Related papers
A Multiple Case Study of Artificial Intelligent System Development in Industry
This investigation revealed different types of AI systems and different AI development approaches, but it is common that business opportunities involving with AI systems are not validated and there is lack of business-driven metrics that guide the development ofAI systems.
Experimenting with Multi-Agent Software Development: Towards a Unified Platform
A unified platform that utilizes multiple artificial intelligence agents to automate the process of transforming user requirements into well-organized deliverables, including user stories, prioritization, and UML sequence diagrams, along with the modular approach to APIs, unit tests, and end-to-end tests.
Bridging Humans and LLMs: Investigating Human-AI Collaboration in Multi-agent Requirements Analysis for Organizational AI Adoption
LLM-based multi-agent systems can support strategic AI planning by enabling iterative refinement with human experts by supporting structured and collaborative Requirements Engineering processes for AI adoption planning.
Constitutional Midtraining: Content Presence Drives Alignment Gains
Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when cleanly isolated from post-training. We build a 394M-token constitutional corpus from Anthropic's Constitution and apply constitutional midtr...