63 long-form pieces on architecture, training, inference, agents and safety.
Training a frontier model is a one-time expense measured in millions. Serving it to users is a perpetual expense measured in billions of tokens per day. For most organisations, inference is already the larger number, and the gap …
A 512-token model could read a paragraph. A million-token model can read a novel. The journey between those two numbers is a story about quadratic cost, clever approximations, and what it means for a machine to "remember."
The protocols that let agents read your email, query your database, and post to Slack were the most-adopted infrastructure in AI over the past year. They also handed attackers a way in that no input filter can close, because the …
A guardrail is a classifier sandwich wrapped around your model, and every layer you add buys coverage with latency and false refusals. Here is how the layer actually works, what it costs, and where it breaks.
The most consequential AI release of late 2024 was not a model. It was a protocol. The story of how a single open standard ended the N-times-M integration nightmare is the story of every standard that ever mattered.
o3, R1 and Claude extended thinking are a real capability shift on a narrow slice of tasks. They are also being shoved into product surfaces that punish every property reasoning models exhibit - and the bill is starting to arrive.
Most long-context models compress the past into a fixed-size vector and hope nothing important got squeezed out. Titans instead gives the model a small neural network as its memory, and lets that network keep training on the data…
For years, sparse attention was a bolt-on applied after training to shrink the KV cache. NSA, MoBA, and DeepSeek's DSA flip that order, training the sparsity end to end and reporting up to 11x faster decoding without losing accuracy.
The Act passed in 2024, the GPAI rules went live in August 2025, and enforcement powers arrive in August 2026. Most Series-A startups need a handful of specific changes, not a compliance department.
We pitted twelve sklearn algorithms head-to-head on a tabular dataset. The winner was not the most expensive one. It was not the most modern one. It was the one whose assumptions matched the data.
A strong model grading other models looks like a free lunch for evaluation. It is not. Position, verbosity, and self-preference biases plus quietly leaked test sets mean a leaderboard number can move several points without any mo…
The industry frames every LLM feature as an agent. Most production systems that work are pipelines with one or two LLM steps and clear handoffs. Default to a workflow, reach for an agent only when the problem demands it.