Type
System Design.
Arguments about where the parts of a system belong, which is usually a more consequential question than which model is used.
18 papers · Type
Mixture of experts: what actually changed
Expert counts went from 8 to 896 in under three years, and that is the least interesting thing that happened. The share of a model that runs for any given token fell from 27.6 per cent to 3.7. A reading of the three structural changes that made that possible: experts small enough to compose rather than choose between, a shared expert holding what every token needs, and load balancing moving out of the loss function and into a controller beside it.
Read the paper →- October 2026ResearchAGA-43
Memory leaves the model
Two papers published four days apart in September 2026 reach the same structural conclusion from opposite ends of the stack. Jev-Mem takes the language model off the critical path of memory operations and reports a 6.6 times faster build, 36.7 per cent lower query latency, and accuracy that went up rather than down. Memory as Middleware argues memory should not live inside an agent at all. When an efficiency argument and a governance argument independently recommend the same boundary, the boundary is usually real.
Luis Hasanaj · Read → - October 2026ResearchAGA-45
Where a hybrid model puts its massive activations
In a dense Transformer the enormous outlier activations sit at a plateau across most of the depth. Interleave linear attention with full attention, as Kimi Linear, Qwen3.5, Nemotron-H and Zamba2 all do, and they reorganise: a sharp spike in the layer immediately before every full attention layer, with 99.4 to 100 per cent alignment, plus plateaus between spikes once attention gets dense enough. Deleting four of those coordinates per attention layer costs up to 88 per cent of retrieval accuracy. A reading of the write-sink-cancel mechanism, the interventions, and why we think this makes hybrids easier to quantise rather than harder.
Luis Hasanaj · Read → - October 2026EngineeringAGA-40
OpenShell puts the enforcement outside the agent
NVIDIA has open-sourced a runtime for AI agents whose central claim is about location rather than capability: enforcement happens outside the agent's process, where it cannot be prompted away. A reading of the four parts, the formal policy prover, the credential that never enters the workload, and the point at which the open source runtime becomes a reference design for hardware NVIDIA sells.
Luis Hasanaj · Read → - October 2026ResearchAGA-38
Kimi K3: where the compute went
Moonshot AI's Kimi K3 technical report makes a compute claim rather than a quality one: roughly 2.5 times more validation accuracy per unit of training compute than Kimi K2, measured recipe against recipe with no component ablations. A reading of Kimi Delta Attention, the 896 expert mixture, the nine specialists merged into one shipped model, and the resumable training harness that is the least glamorous and most transferable idea in it.
Luis Hasanaj · Read → - September 2026OperationsAGA-33
WhatsApp is already your customer record
For a great many small businesses the real history of every customer relationship sits in WhatsApp threads on individual phones. It is the most complete record in the company and the least owned by it. What it takes to bring that into a system without breaking consent, and why the first thing to fix is not automation.
Luis Hasanaj · Read → - September 2026EngineeringAGA-30
OpenAI's dots: the boundary is the product
OpenAI launched always-on personal agents at DevDay, each running on its own cloud computer with a browser and access to more than 4,000 apps. The marketing is autonomy. The engineering is a carefully drawn permission boundary, and the single most important decision in it is that an agent left running while you are away can only read.
Luis Hasanaj · Read → - September 2026EngineeringAGA-35
Hardware-native AI: the alarm that sees
A position paper. The next operating system layer will be built into devices rather than shipped as an app on top of them, and home security is the clearest worked example: an alarm today is a deterrent that detects motion, while a camera that understands what it is looking at is a different category of thing. The interesting engineering is not the vision model. It is deciding how far up the response ladder a device may go without a person.
Luis Hasanaj · Read → - September 2026ResearchAGA-36
A chain of events beats one big model
A position paper. An operating system is not a conversation, it is a chain of recurring events, each one narrow and shaped the same way every time. Give each event deterministic control flow, its own memory and a small tuned model, and the arrangement beats a general language model orchestrating everything, on latency, cost and predictability. The honest limit is what a fleet of specialists costs to operate.
Luis Hasanaj · Read → - September 2026OperationsAGA-32
What an AI receptionist actually fixes
Most of the market sells this as never miss a call again. The honest version is narrower and more useful: it fixes the calls you were never going to answer, it does not fix the calls where the conversation is the product, and the deciding question is which of those you mostly get. A buyer's guide from a company that builds one.
Luis Hasanaj · Read → - September 2026OperationsAGA-34
AI implementation is an architecture decision
Most AI projects that fail do not fail on the model. They fail because nobody wrote down the number that should move, and because a slow expensive model was put somewhere a person was waiting. The three axes that actually decide an implementation are cost per completed task, speed to a finished outcome, and latency, and only one of them appears on a price list.
Luis Hasanaj · Read → - September 2026ResearchAGA-27
CLM-8B, Jev, and language model shape
In one week, four independent groups published work that stops treating the language model as a fixed-shape black box: a model that ranks instead of generating, one whose output is constrained to a single number, one that varies depth per token, and one that changes the generation order. Reading them together, and the engineering bill nobody is itemising.
Luis Hasanaj · Read → - September 2026EngineeringAGA-26
TypeSafe's System One: code orchestrates
A new model class argues that the control flow belongs in your code and the model should be a typed function call returning a calibrated probability. It is the strongest published case yet that the deterministic core is the cheap, fast, reliable part, and that putting a language model in charge of the loop is a transitional architecture rather than the destination.
Luis Hasanaj · Read → - September 2026EngineeringAGA-24
GPT-6 Astra's system card is a build spec
Read as safety documentation it is reassuring. Read as an engineering requirement it is a list of things your infrastructure now has to do: a halt state you do not control, an approval gate a machine must not be able to satisfy, credentials the model will find, and oversight that no longer rests on reading the model's reasoning.
Luis Hasanaj · Read → - September 2026EngineeringAGA-18
Tinker, Inkling and the return of fine tuning
Thinking Machines Lab is betting that models an organisation can adapt will beat the one size fits all models the big labs sell. What Tinker and Inkling actually are, why LoRA and per token pricing changed the economics, and the test that tells you whether your problem needs fine tuning or just better retrieval.
Luis Hasanaj · Read → - September 2026EngineeringAGA-15
AI agent security: the real attack surface
An agent with credentials, tools and memory is not a chatbot with a bigger prompt, it is software that acts. This is the attack surface that creates, read against the OWASP Top 10 for Agentic Applications 2026, two live CVEs in agent infrastructure, and the first reported cyber espionage campaign run mostly by hijacked agents.
Luis Hasanaj · Read → - August 2026EngineeringAGA-10
Engineering for the EU AI Act: Article 50 transparency as system architecture
How we build the EU AI Act's Article 50 transparency duties into AI-native products as architecture rather than configuration: disclosure at first contact, provenance marking at generation, recorded human review and per-message jurisdiction, read against the timeline as amended by the 2026 Digital Omnibus.
Luis Hasanaj · Read → - January 2026EngineeringAGA-01
GPU Query Engine (GQE): a reference architecture for GPU-accelerated SQL
A reference architecture for a GPU-accelerated SQL engine, built on libcudf and NVCOMP, that pushes complex analytics query processing to speed-of-light on modern GPUs.
Luis Hasanaj · Read →