2251
Compiling LLMs into a MegaKernel: A path to low-latency inference
TL;DR: We developed a compiler that automatically transforms LLM inference into a single megakernel — a fused GPU kernel that performs…
New
The latest blog posts to take off on Hacker News. 6,329 posts.
2252
How OpenElections uses LLMs
In the 12-plus years that we’ve been turning official precinct election results into data at OpenElections , the single biggest problem has been converting pictures of results into CSV files. Many of the precinct results files we get are image PDFs, and for those there are essentially two options: data entry or…
2253
From LLM to AI Agent: What's the Real Journey Behind AI System Development?
Confused by LLMs, RAG, & AI Agents? We break down the spectrum of AI system design with a familiar resume-screening example to show the leap in capabilities (and complexity) at each level.
2254
Remote MCP Support in Claude Code
Connect your favorite development tools and data sources securely to Claude Code through remote MCP servers. Today, we’re announcing support for remote MCP servers in Claude Code.
2255
Andrej Karpathy's talk on the future of the industry
Transcript of Andrej Karpathy's YC AI SUS talk at Y Combinator on June 17th, 2024.
2256
Revisiting Minsky's Society of Mind in 2025
AI Agents, Modularity, and Alignment
2257
Building agents using streaming SQL queries
Table of Contents Agents Need to Interact With LLMs Agents Should Be Event-Driven Agents Need Context Agents Require Memory When SQL Is Not Enough Parting Thoughts AI Agents have improved in leaps …
2258
Is there a half-life for the success rates of AI agents?
Building on the recent empirical work of Kwa et al. (2025), I show that within their suite of research-engineering tasks the performance of AI agents on longer-duration tasks can be explained by an extremely simple mathematical model — a constant rate of failing during each minute a human would take
2259
I counted all of the yurts in Mongolia using machine learning
The Fall of Civilizations podcast put out a 6¾-hour episode on the history of the Mongol Empire, which I eagerly listened to. After finishing the episode I wondered about contemporary Mongolian society, I wanted to learn what the lands that the Mongol Empire exploded from are like in our current day. There are many…
2260
Your Brain on ChatGPT
Check project's website: https://www.brainonllm.comWith today's wide adoption of LLM products like ChatGPT from OpenAI, humans and businesses engage and u…
2261
What Google Translate can tell us about vibecoding
There has been rather a lot of doomsaying (and perhaps astroturfing) lately about LLMs as the end of computer programming. Much of the discussion has been lacking nuance, so I’d like to add mine. I see claims from one side that “I used $LLM_SERVICE_PROVIDER to make a small throwaway tool, so all programmers will be…
2262
LLMs pose an interesting problem for DSL designers
The most exciting part of Programming Languages (PL) research for me has always been in Programming Language Design.
2263
Time Series Forecasting with Graph Transformers
Introduction to Kumo Relational — the relational foundation model for predictive AI on relational data
2264
Building Effective AI Agents
Practical guidance from Anthropic on building reliable AI agents, from simple composable patterns to fully autonomous systems.
2265
Making 2.5 Flash and 2.5 Pro GA, and introducing Gemini 2.5 Flash-Lite
Gemini 2.5 Flash and Pro are now generally available, and we’re introducing 2.5 Flash-Lite, our most cost-efficient and fastest 2.5 model yet.
2266
2267
O3 Turns Pro
You can now have o3 throw vastly more compute at a given problem.
2268
Claude Code feels like magic because it is iterative
Personal blog of Omar Abid
2269
Generative AI coding tools and agents do not work for me
People keep asking me If I use Generative AI tools for coding and what I think of them, so this is my effort to put my thoughts in writing, so that I can send people here instead of having to repeat…
2270
The drawbridges come up: the dream of a interconnected context ecosystem is over
The AI era is speedrunning the Web 2.0 story. Open and accessible MCPs are not our future. Integrations will be tightly governed.
2271
Snorting the AGI with Claude Code
blog - kade killary
2272
Meta's Llama 3.1 can recall 42 percent of the first Harry Potter book
New research could have big implications for copyright lawsuits against generative AI.
2273
Q-learning is not yet scalable
Over the past few years, we've seen that next-token prediction scales, denoising diffusion scales, contrastive learning scales, and so on, all the way to the point where we can train models with billions of parameters with a scalable objective that can eat up as much data as we can throw at it. Then, what about…
2274
Seven replies to the viral Apple reasoning paper and why they fall short
Also: another paper that seals the deal
2275
Design Patterns for Securing LLM Agents Against Prompt Injections
This new paper by 11 authors from organizations including IBM, Invariant Labs, ETH Zurich, Google and Microsoft is an excellent addition to the literature on prompt injection and LLM security. …
2276
Agentic Coding Recommendations
Current recommendations of agentic coding.
2277
The first big AI disaster is yet to happen
The first public passenger locomotive, Locomotion No. 1, began service in September 1825. The first mass-casualty railway disaster happened seventeen years…
2278
2279
V-JEPA 2 world model and new benchmarks for physical reasoning
We’re excited to share V-JEPA 2, the first world model trained on video that enables state-of-the-art understanding and prediction, as well as zero-shot planning and robot control in new environments.
2280
AI at Amazon: A case study of brittleness
A year ago, Mihail Eric wrote a blog post detailing his experiences working on AI inside Amazon: How Alexa Dropped the Ball on Being the Top Conversational System on the Planet. It’s a great …