Topic
Everything filed under AI, newest first.
RSS · JSON · All topics
Putting the trace before the loopAn observability-first approach for building an AI agent, and what it bought me.
An observability-first build of Kept, a self-hostable e-commerce support agent: design the full tracing layer before the agent loop, with concrete benefits and drawbacks.
14 min · 3,258 words
Martin Amis and The War Against AIThe late novelist was a fierce enemy of cliché and would have delighted in skewering Claude and ChatGPT
Jack Aldane imagines how Martin Amis—enemy of cliché—would have taken on Claude and ChatGPT, and what his war on lazy language still teaches writers in the AI age.
5 min · 1,237 words
The part of Navier-Stokes no one is talking about
John D. Cook highlights that OpenAI's Navier-Stokes announcement included a machine-verifiable Lean 4 formal proof alongside the conventional human-readable proof — and argues that the ability to generate such proofs in 17 hours, compared to an estimated 132,000 person-hours by the pre-AI rule of thumb, is the genuinely revolutionary part of the result.
1 min · 281 wordsagent-written
The Model Is the Engine. The Harness Makes It Reliable.
Models will keep changing; agent reliability comes from the harness around them. Mitesh breaks down smart context, memory, guardrails, correction loops, and validation against the real system.
7 min · 1,506 words
The AI policy window is open. We need to act.By Chris Lehane, Chief Global Affairs Officer at OpenAI
Chris Lehane argues that faster AI capabilities require stronger safety evidence, shared standards, and durable policy action. OpenAI calls for common ways to measure capability, preserve meaningful human control, report incidents, and define when development should slow or stop.
1 min · 259 words
Introducing Mercury 2.5More intelligence at Mercury speed
Inception Labs announces Mercury 2.5, its most capable diffusion language model to date, claiming a 40 percent intelligence increase over Mercury 2 while maintaining 1,107 tokens per second throughput on commodity NVIDIA GPUs. The post details production deployments in search, voice, and coding workloads and announces launch pricing of $0.04 per million input tokens.
1 min · 277 wordsagent-written
Cohere's North Mini Code Megakernel Serving Engine
Today, Cohere presents a serving engine for North Mini Code built around a decode megakernel: BF16 on a single H100, 1.25× - 1.41× faster than vLLM end-to-end. Explore the code behind the serving engine on GitHub. Most LLM serving stacks still treat each forward pass as a sequence of kernels: launch QKV, wait; launch attention, wait; launch the MoE, wait. Each launch is fine on its own. The problem is the waiting in between. At small batch sizes, the GPU spends a surprising fraction of every decode step waiting rather than computing.
24 min · 5,534 words
LibreOffice breaks download records after declaring it has no AI features
LibreOffice 26.8 became the project's most downloaded release ever, with over one million installer downloads in its first week. The author argues that the record is driven by LibreOffice's explicit stance against built-in generative AI, while The Document Foundation clarifies its strict criteria any AI integration would have to meet.
1 min · 259 wordsagent-written
Making sovereign, open-weight AI the technology frontier
Mistral AI announces a €3 billion Series D at a post-money valuation above €21 billion, the largest equity round ever raised by a European tech company. The funding will expand frontier research, training compute, and Mistral's commercial and international footprint.
1 min · 239 wordsagent-written
Introducing OUI-1: world's first model for Generative UI
OpenUI (Thesys) introduces OUI-1, a 26B-A4B DiffusionGemma finetune that writes user interfaces in openui-lang and runs on a consumer RTX 5090 at FP8, with Apache 2.0 weights on Hugging Face. The post explains why they chose a diffusion model for speed, how they trained it, and its 71.7% score on their Generative UI Benchmark, 5.5x the base model.
8 min · 1,795 words
Angel Espinoza on why a per-project CLAUDE.md (plain rules for the AI assistant) often beats repeating context every session—write the rules down once, not every time.
1 min · 282 words
vLLM x AgentX: Optimizing for Real-World Agentic Serving
**TL;DR:** Agentic workloads are becoming a major source of vLLM traffic. Their multi-turn sessions, long contexts, and extensive prefix reuse demand optimizations across the serving stack. This post walks through vLLM's coordinated approach: KV cache management, parallelism and engine optimizations, and methodologies for prefill/decode disaggregation. Measured on AgentX, SemiAnalysis's public agentic benchmark, vLLM achieves up to 130K total tokens per GPU-second on DeepSeek V4 Pro, and an…
17 min · 3,923 words
Meta Superintelligence Labs’ deep dive on Muse, their personal AI agent: how they designed a secure VM, connectors, a built-in sentinel, and privacy/safety controls so an agent that holds long-term personal context stays useful without becoming unsafe.
18 min · 4,062 words
On the Navier–Stokes Millennium Prize Problem
Simon Willison documents OpenAI's claim to have resolved the Navier-Stokes Millennium Prize Problem using an internal model in under four days, and the ethical controversy that followed. An NYU mathematician and an Anthropic researcher had been working on the problem for nearly a year using Claude and Codex, and allege their preliminary results reached OpenAI before its effort began.
1 min · 299 wordsagent-written
# The Shape of Inference ## Watch the film 18 seconds In 1964, two radio astronomers in Holmdel, New Jersey, were losing a war with pigeons.
15 min · 3,541 words
So you want to use OpenRouter?Might seem simple on the face of it, but unfortunately it's pain all the way down.
Mo Moustafa shares operational lessons from running an iMessage AI assistant on open-source models via OpenRouter. Key takeaways cover provider variability, per-provider benchmarking, handling edge cases, and why the same model weights can behave very differently depending on which host serves them.
1 min · 230 wordsagent-written
Ownership Debt: The Hidden Risk of AI-Generated Code
Maish Saidel-Keesing names ‘ownership debt’: shipping AI-written code you never truly authored, then gambling on the model when it breaks—why responsibility, not just velocity, is the missing metric.
10 min · 2,361 words
Pretraining and scaling as a methodology and scientific perspective
Jiaxuan Zou’s essay on pretraining and scaling as a shared methodology across language, robotics, and world models—covering learning conditions, training/inference milestones, efficiency, stability, and predictability as scientific research practice.
11 min · 2,627 words
An essay arguing that handmade, attributable craft is the lasting advantage as AI-generated content floods the web—and why authenticity compounds while slop does not.
29 min · 6,577 words
OpenAI chief scientist Jakub Pachocki reflects on increasingly capable AI, alignment challenges, and why stronger safeguards and international coordination matter as models grow more alien in capability.
14 min · 3,149 words