751
Introducing the Llama Startup Program
We’re excited to announce the Llama Startup Program, a new initiative to empower early stage startups to innovate and build generative AI applications with Llama.
Top posts
Every blog post that took off on Hacker News, ranked by the votes of its best submission. 1,227 posts.
752
About AI Evals
A guide to AI and LLM evals for engineers and product managers. Learn how to test AI systems, analyze failures, and improve retrieval, agents, and AI products.
753
Gemini figured out my nephew’s name
I wrote an MCP server to give LLMs read-only access to my emails. Here is the chat log.
754
Arc-AGI-2 and ARC Prize 2025
Measuring the next level of intelligence with ARC-AGI-2 and ARC Prize 2025
755
Are polynomial features the root of all evil? (2024)
High-degree polynomial features aren’t inherently unstable: the power basis and unscaled inputs are. This post shows how regularization and Bernstein polynomials make polynomial regression behave.
756
Yes, Claude Code can decompile itself. Here's the source code
These LLMs are shockingly good at deobfuscation, transpilation and structure to structure conversions. I discovered this back around Christmas where I asked an LLM to make me an Haskell audio library by transpiling a rust implementation. An “oh fuck” moment in timeOver the Christmas break I’ve been critically looking
757
Building AI agents to query your databases
In the world of AI agents, the ability to understand and analyze structured data is a game-changer. While large language models excel at understanding natural...
758
Speeding up PyTorch inference on Apple devices with AI-generated Metal kernels
Our lab investigated whether frontier models can write optimized GPU kernels for Apple devices to speed up inference. We found that they can: our AI-generated Metal kernels were 1.24x faster across KernelBench v0.1 problems, and 1.87x faster across KernelBench v0 problems.
759
Starcloud
The NVIDIA Inception startup projects that space-based data centers will offer 10x lower energy costs and reduce the need for energy consumption on Earth.
760
MCP vs. API Explained
Model Context Protocol (MCP) is an open standard that connects AI models to tools and data sources efficiently. This guide breaks down MCP’s architecture, benefits, and how it differs from traditional APIs
761
Orpheus-3B – Emotive TTS by Canopy Labs
Canopy Labs is developing digital humans that are indistinguishable from real ones.
762
Finding Signal in the Noise: Machine Learning and the Markets (Jane Street)
Listen in on Jane Street’s Ron Minsky as he has conversations with engineers working on everything from clock synchronization to reliable multicast, build systems to reconfigurable hardware. Get a peek at how Jane Street approaches problems, and how those ideas relate to tech more broadly.
763
AI agent benchmarks are broken
Benchmarks are foundational to evaluating the strengths and limitations of AI systems, guiding both research and industry development.
764
The Future of MCPs
MCPs—Model Context Protocols—are set to transform AI from passive chatbots into powerful, action-taking agents. But the real story isn’t what MCPs enable—it’s who controls them.
765
Build your own Siri locally and on-device
That doesn’t spy on you
766
A visual exploration of vector embeddings
For Pycon 2025, I created a poster exploring vector embedding models, which you can download at full-size . In this post, I'll translate ...
767
How to scale your model: A systems view of LLMs on TPUs
Training LLMs often feels like alchemy, but understanding and optimizing the performance of your models doesn't have to. This book aims to demystify the science of scaling language models: how TPUs (and GPUs) work and how they communicate with each other, how LLMs run on real hardware, and how to parallelize your…
768
AI Responses May Include Mistakes
The other day I wanted to look up a specific IBM PS/2 model, a circa 1992 PS/2 Server system. So I punched the model into Google, and got this:
769
Softmax forever, or why I like softmax
[UPDATE: Feb 8 2025] my amazing colleague Max Shen noticed a sign mistake in my derivation of the partial derivative of the log-harmonic function below.
770
771
The skill of the future is not 'AI', but 'Focus'
Don't let AI erode your focus.
772
Coping with dumb LLMs using classic ML
Taking the output of many dumb LLM search relevance judges and feeding the output to a decision tree to improve precision
773
Structured outputs on the Claude Developer Platform
Structured outputs on the Claude Developer Platform guarantee API responses match your JSON schemas and tool definitions. Now in public beta for Sonnet 4.5 and Opus 4.1, this feature eliminates parsing errors and failed tool calls for production applications.
774
LoRA Without Regret
How LoRA matches full training performance more broadly than expected.
775
AI Angst
My input stream is full of it: Fear and loathing and cheerleading and prognosticating on what generative AI means and whether it’s Good or Bad and what we should be doing. All the channels: Blogs and peer-reviewed papers and social-media posts and business-news stories. So there’s lots of AI angst out there, but this…
776
Developers are choosing older AI models
At Augment Code, we run multiple frontier models side by side in production. This gives us a unique vantage point into how different models behave in real…
777
Signs of introspection in large language models
Research on the ability of large language models to introspect on their own internal states.
778
Best Practices for Building Agentic AI Systems
Patterns that keep AI agent systems from falling apart in production: two-tier architecture, stateless design, orchestration, and lessons from UserJot.
779
Hidden risk in Notion 3.0 AI agents: Web search tool abuse for data exfiltration
CodeIntegrity research on Notion AI security, Notion 3.0 AI Agents, lethal trifecta risk, indirect prompt injection, web search tool abuse, and data exfiltration.
780
I passionately hate hype, especially the AI hype
I truly and passionately hate hype. From the fakeness of it to the sheer stupidity it represents, but perhaps most of all, because of the devastating consequence it often results in.