Towards AI

One endpoint is convenient. One endpoint that quietly rewrites your model request is an outage waiting for a release you did not control. An agent works perfectly in a direct provider sandbox. It streams, calls tools, keeps a long context warm, and returns a strict object your application can trust. Then the team moves it behind an LLM gateway to centralize billing and policy. A new model setting disappears. A usage field no longer arrives. A streaming tool loop stalls. Nothing crashes loudly enough to make the cause obvious. This is the hidden trade-off in multi-provider AI: a gateway can mak

How I ported a Python eval-driven setup to C#, why my LLM judge gave a dangerous answer a perfect score, and what I changed in the rubric afterwards. The moment I decided to take evals on my .NET agent seriously was not dramatic. I changed one sentence in a system prompt, ran the agent by hand four times, liked what I saw, and shipped it. Two days later I wanted to know whether that change had made anything worse. The only way I had to find out was to run the agent again, against a model, and squint at the output. That is the expensive way to answer a cheap question. Most of what I wanted to k

AI Code Review Blast Radius A faster coding agent does not make every change equally safe. The teams that keep speed are learning to route review attention by risk, not by who -or what-wrote the code. Your AI coding agent opens a pull request that looks clean. Tests are green. The diff is only 180 lines. Then a reviewer notices that one of those lines changes how a tenant is selected before an authorization check. The patch was small; its blast radius was not. That is the review problem many engineering teams have now. Agents can create more changes than a small group of people can read with u

The AI developer workflow is shifting from writing code to managing agents. Continue reading on Towards AI »

Your lakehouse doesn’t slow down because the data grew. It slows down because the file count did — and every one of those files is a tax your query planner pays before it reads a single byte. Part I | Part II | Part III | Part IV | Part V | Part VI | Part VII | Part VIII | Part IX | Part X | Part XI | Part XII | Part XIII | Part XIV | Part XV | Part XVI | Part XVII | Part XVIII The 58-Minute Query That Read Nothing Useful The Slack message landed at 9:41 PM, eleven minutes into the nightly reporting window: “finance dashboard is stuck again.” Not failed — stuck. The aggregate query over our ev

Inside EdgeRock-4B’s “Rock Memory Anchors” — and what they mean for anyone serving long-reasoning models Every engineer who has served a reasoning model knows the moment. The model is good, the answers are right, and then someone sends a 64K-token agent trace and the GPU's memory graph turns into a staircase. Reasoning models think out loud, and every token they think costs KV cache. On October 19, 2026, a team from Rock Matrix (岩芯矩阵, a unit of Chinese listed company 岩山科技), working with researchers at HKUST and CMU, open-sourced a model that takes a different route. EdgeRock-4B keeps its atten

Two 90° turns can leave an object facing two different ways, depending only on which turn comes first. Continue reading on Towards AI »

Fewer junior hires, six agent hours for every human hour and a new category of work called meta-work: the most honest preview yet of what… Continue reading on Towards AI »

I have a WordPress project running on PHP 8.3.6, and on Wednesday the version I need to be on became 8.3.36. That is the whole of my… Continue reading on Towards AI »

A session graph, shortest paths and a knapsack kept every rule at half the tokens of a summary. Then the next task cost twice as much. I looked at the compactions in my own long Claude Code sessions. Each /compact read between 437k and 830k tokens, took 134 to 182 seconds, and produced a summary of 20k to 28k characters. That summary is everything the rest of the session knows about what came before. A model wrote it in one pass, deciding on its own what would matter later. Two things about that bothered me. First, a summary paraphrases. “Amounts are integer cents end to end” can come back as

From one GPU’s tile grid to vLLM clusters and DeepSeek’s DeepInfer Continue reading on Towards AI »

Every Clock Says 10:10? How AI Actually Generates Images — Diffusion, Latent Space & Flow Matching (Every Number Measured) Why every AI clock snaps to 10:10, how a 32-channel VAE cuts attention 65,536×, Tweedie’s formula, Classifier-Free Guidance, and 4-step Rectified Flow measured on a 96 GB Blackwell GPU. By Latent AI Labs (@LatentAILabs) In Part 1 ( YouTube ), we saw how an LLM turns words into vectors and why it miscounts the "r"s in "strawberry". In Part 2 ( YouTube ), we measured how thinking models catch their own mistakes by writing a scratchpad. And in Part 3 ( YouTube ), we opened al

How a GTX 1650 Ti handled 64K context, turned 106-second prompts into subsecond repeats, and ran a real coding agent. Continue reading on Towards AI »

The AI brain isn’t what you think it is. 🔥🧠 Continue reading on Towards AI »