2221
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.
New
The latest blog posts to take off on Hacker News. 6,329 posts.
2222
The new skill in AI is not prompting, it's context engineering
Context Engineering is the new skill in AI. It is about providing the right information and tools, in the right format, at the right time.
2223
There are no new ideas in AI, only new datasets
LLMs were invented in four major developments... all of which were datasets
2224
We accidentally solved robotics by watching 1M hours of YouTube
the existential crisis we all share imagine this: you've just spent $640 billion training the chonkiest language model known to humanity (lol) and decide...
2225
Life of an inference request (vLLM V1): How LLMs are served efficiently at scale
vLLM is an open-source inference engine that serves large language models. We deploy vLLM across GPUs and load open weight models like Llama 4 into it. vLLM sits at the intersection of AI and systems programming, so we thought that diving into its details might interest our readers.
2226
MCP: An (Accidentally) Universal Plugin System
Or: The Day My Toaster Started Taking Phone Calls
2227
Normalizing Flows Are Capable Generative Models
Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density…
2228
Project Vend: Can Claude run a small shop? (And why does that matter?)
We let Claude run a small shop in the Anthropic office. Here's what happened.
2229
Qwen VLo: From “Understanding” the World to “Depicting” It
QWEN CHAT DISCORD Introduction The evolution of multimodal large models is continually pushing the boundaries of what we believe technology can achieve. From the initial QwenVL to the latest Qwen2.5 VL, we have made progress in enhancing the model’s ability to understand image content. Today, we are excited to…
2230
AI Is Dehumanization Technology
A call to reject the deployment and use of AI systems in Canada's public sector.
2231
Introducing Gemma 3n
Learn how to build with Gemma 3n, a mobile-first architecture, MatFormer technology, Per-Layer Embeddings, and new audio and vision encoders.
2232
FLUX.1 Kontext [Dev] – Open Weights for Image Editing
Up until today, all capable generative image editing models were only available as proprietary tools.
2233
AlphaGenome: AI for better understanding the genome
Introducing a new, unifying DNA sequence model that advances regulatory variant-effect prediction and promises to shed new light on genome function — now available via API.
2234
Learnings from building AI agents
How cubic reduced noisy AI code review comments with reasoning logs, fewer tools, specialized agents, and evaluation before changes reached production.
2235
2236
MCP in LM Studio
New in LM Studio 0.3.17: Model Context Protocol (MCP) Host support. Connect MCP servers to the app and use them with local models.
2237
Build and Host AI-Powered Apps with Claude – No Deployment Needed
Build and share AI-powered apps directly in Claude. Update: Now available on Team and Enterprise plans. (July 31, 2025) Update: Upload PDFs, images, and more into your artifact.
2238
Bot or human? Creating an invisible Turing test for the internet
Behavioral and cognitive patterns distinguish humans from bots. Explore interactive demos and a practical framework for invisible Proof of Human.
2239
Is Lovable getting monetization wrong?
The current (and future) monetization strategies of "Shopify for SaaS"
2240
OpenAI charges by the minute, so speed up your audio
I discovered a fun and strangely obvious trick for summarizing videos faster and reducing costs: just speed them up. Cheaper, faster OpenAI transcriptions with a little ffmpeg trick.
2241
Gemini CLI
Free and open source, Gemini CLI brings Gemini directly into developers’ terminals — with unmatched access for individuals.
2242
Reinforcement learning, explained with a minimum of math and jargon
To create reliable agents, AI companies had to go beyond predicting the next token.
2243
The bitter lesson is coming for tokenization
Highlights the desire to replace tokenization with a general method that better leverages compute and data. We'll see tokenization's fragility and review the Byte Latent Transformer arch.
2244
Gemini Robotics On-Device brings AI to local robotic devices
We’re introducing an efficient, on-device robotics model with general-purpose dexterity and fast task adaptation.
2245
The NO FAKES act has changed, and it's worse
A bill purporting to target the issue of misinformation and defamation caused by generative AI has mutated into something that could change the internet forever, harming speech and innovation from here on out.The Nurture Originals, Foster Art and Keep Entertainment Safe (NO FAKES) Act aims to...
2246
TPU Deep Dive
I've been working with TPUs a lot recently and it's fun to see how they had such different design philosophies compared to GPUs.
2247
MCP is eating the world
Despite the hype, Model Context Protocol (MCP) isn’t magic or revolutionary. But, it’s simple, well-timed, and well-executed. At Stainless, we’re betting it’s here to stay.
2248
Agentic Misalignment: How LLMs could be insider threats
New research on simulated blackmail, industrial espionage, and other misaligned behaviors in LLMs.
2249
Phoenix.new – Remote AI Runtime for Phoenix
Documentation and guides from the team at Fly.io.
2250
AI is going to hack Jira
Hide your kids, hide your wife: how the Agile Industrial Complex has set us all up to be duped by AI codegen