Tag
The author fine-tuned a model on their bookmarks to create a personalized content recommendation algorithm that scans social media and research papers daily, adapting to user feedback.
This megathread compiles a list of the latest open-source projects, research papers, and hardware innovations focused on optimizing inference, efficiency, and accessibility for open-source LLMs and related technologies.
This newsletter covers key AI and tech news, including a Pew study indicating that a third of web pages published since ChatGPT's launch show signs of AI authorship, alongside updates on enterprise competition and research on agent safety.
The newsletter covers major AI industry developments, including a $500 billion investment by Wall Street firms into Nvidia's AI infrastructure, Anthropic's upcoming IPO plans, and summaries of recent research papers on AI reasoning and agent failures.
The article emphasizes that software engineering fundamentals remain crucial in the age of AI and agentic tools, highlighting the reasoning limitations of LLMs and the need for maintainable, well-designed software.
A user created an interactive atlas that maps 8.5 million research papers for exploration and discovery.
OpenDraft is an open-source tool that uses 19 specialized AI agents in parallel to assist with research paper writing and literature reviews, described as 'Claude Code for research papers'.
Two papers published this week address agent memory poisoning and privacy leaks, but no readily usable library or tool has been released to implement these fixes.
A tweet lists 10 essential research papers for ML engineer interviews, covering foundational topics from Word2Vec to GPT.
A list of essential research papers for LLM engineers, including key works on transformers, scaling laws, and fine-tuning techniques.
The article distills 28 research papers into a 10-layer stack for building self-improving harnesses around AI models, emphasizing bounded, gated changes over general agent loops.
A tweet introduces how to combine Keshav's three-pass method to efficiently read academic papers in the AI era, emphasizing AI tools for compressing noise, explaining complex concepts, and adversarial training, while reminding readers to maintain critical thinking and academic taste.
World Labs announces three new research papers focused on generating 3D content using large-scale generative models and 2D priors, led by interns Hao Zhang, Bert Duisterhof, and Ben Tunnels.
A developer shares how they reduced their AI agent's weekly cost from $200 to $40 by routing simple subtasks to cheaper models like DeepSeek V4 Pro and Tencent Hunyuan while keeping complex reasoning on Opus 4.7, achieving comparable output quality for most work.
A tweet shares a structured reference of 450 papers on GPU optimization spanning 14 years, noting that while some techniques evolve, the mental models remain useful. It also references a lecture on GPU architectures by Onur Mutlu.
A curated list of foundational AI papers recommended for interview prep, covering transformers, efficient fine-tuning, vision models, and generative networks.
Paper2Agent is an automated framework that converts research papers into interactive AI agents to enhance knowledge dissemination and enable complex scientific queries through natural language.