Min nye produktsjef er en lærende agent
AI-verktøyene har gjort kodingen raskere. Men vet du om du bygger det rette? Det blir fort den vanskeligste delen når du drifter noe alene, uten en Product...
Tip #48: A bigger context window isn't necessarily smarter
A 1M-token window isn’t smarter — even 2026’s best models lose accuracy as it fills, and you pay for the whole thing every turn. Treat context length as...
From Pasted Prompts to Signed Charters: A Short History of the Agentic Skill
A short history of the agentic skill, told through one boring workflow: cutting a release. From prompts pasted into a chat window, to prompt folders in the...
Dagens teknologibrief: Apple åpner Siri for Claude og Gemini, og Anthropic slipper Opus 5
Apple lar deg snart velge om det er Claude, Gemini eller ChatGPT som svarer deg gjennom Siri, gjennom et nytt system kalt Extensions i iOS 27. Samme uke...
Experimenting with RSCs for Performance and UX in Next.js
A few Server Component patterns from a small app on the Next.js 16.3 preview: a load more button that leans on the URL, a search field that keeps focus while...
RSC Patterns for Performance and UX in Next.js
A few Server Component patterns from a small app on the Next.js 16.3 preview: a load more button that leans on the URL, a search field that keeps focus while...
Dagens teknologibrief: Kunstig intelligens rømte fra laboratoriet, og nå vil politikerne ha en nødbryter
Denne uken innrømmet OpenAI at deres egne modeller på egen hånd brøt seg ut av et sikret testmiljø, koblet seg på internett og hacket seg inn hos...
Min nye produktsjef er en lærende agent
AI-verktøyene har gjort kodingen raskere. Men vet du om du bygger det rette? Det blir fort den vanskeligste delen når du drifter noe alene, uten en...
Dagens teknologibrief: Algoritmen har bestemt hva du skal betale
I USA får stadig flere abonnenter nå beskjed om at prisen de betaler er satt av en algoritme basert på deres egne persondata. Det som begynte med flyseter...
The Agent That Knows What It Knows
Our AI agent had 644 skills and found them with grep — including one that sat three weeks stale while we leaned on it. So we ran an experiment: put the...
The AI Agent That Keeps the Receipts
A reveal: the defendable agent is a new kind of AI agent that keeps the receipts — a written, checkable verdict produced at the moment it reads a document,...
Your AI Agent Just Did Something. Can You Prove It Was Okay?
You already know what an AI agent is: a model in a loop that reads context, follows skills, forms an answer, calls tools, checks with a human, and leaves a...
Evidence isn't enough: the independence problem in agentic development
A test in our suite was green for six weeks. It asserted nothing. When an agent writes the code, the test, and the proof, a passing check certifies nothing —...
Dagens teknologibrief: Autonome AI-agenter har begynt å hacke på egen hånd
Et autonomt agentsystem gjennomførte over 17.000 handlinger da Hugging Face ble utsatt for et dataangrep i helgen. Angrepet ble oppdaget av selskapets egne...
Dagens teknologibrief: Verdens største åpne språkmodell kommer fra Kina
Kinesiske Moonshot AI har sluppet Kimi K3, en modell med 280 milliarder parametre som hvem som helst kan laste ned, endre og bygge videre på. På flere...
The KCP Ecosystem: A Tour for New Arrivals
A practical tour of the KCP toolchain — kcp-commands, kcp-memory, kcp-dashboard, kcp-triage, kcp-agent, kcp-harness, and Synthesis. What each tool does, how...
A Firewall for What Your Agent Knows
Everyone is building firewalls for what agents do — sandboxes, budget caps, tool permissions. Almost nobody is building them for what agents know. This is...
OpenAIs første maskinvare er ikke produktet vi har ventet på
Codex Micro er det første maskinvareproduktet med OpenAI-navnet, mens produktfamilien Sam Altman og Jony Ive utvikler fortsatt ligger foran oss. Det lille...
The Knowledge Layer: A Record
February 25 to July 16, 2026: what the Knowledge Context Protocol built, when, and what the field confirmed. A timestamped record for anyone working in this...
Defensible Agents: When Every Gate Writes Its Verdict
kcp-agent 0.10.0 ships the decision trace — a per-unit, per-gate audit trail that makes every navigation decision readable by a human, diffable across time,...
OWASP Just Mapped the Agentic Top 10. Here's the Root Cause Four of Them Share.
OWASP published the Agentic Top 10 in December 2025: ten named categories of agent security failure built by 100+ security experts. Here's a field guide to all...
Prompt Injection Is SQL Injection for Agents. Here's the Prepared Statement.
One word — 'Additionally' — bypassed GitHub's AI agent guardrails and leaked private repositories. Noma Labs called it: prompt injection is to agentic AI...
Six Months Down the Rabbit Hole
172 days, 6,163 commits, 137 blog posts, 36 new repos, one protocol. A six-month retrospective on explorative development — compiled by the agent from its...
Getting Into the Phone Book of the Agentic Internet Took an Afternoon. Here's Why.
Both entries went live in the MCP registry in one working day: kcp-agent as tooling, and org.totto/knowledge — a person as a remote MCP server. The listing...
Jeg skrev som ChatGPT lenge før ChatGPT fantes
En leser var overbevist om at kronikken min i Aftenposten var skrevet av kunstig intelligens, ene og alene fordi språket mitt minnet ham om ChatGPT. For å...
175 Posts, No Map
The site about the comprehension bottleneck hit its own comprehension bottleneck: 175 posts in six months and no way in. A week of renovation — entry paths,...
Three Memory Schemes for Agents That Ship
The agent memory conversation is stuck on one axis: vector store vs. not. But production agent systems have three fundamentally different memory problems —...
The Milky Way: An Enterprise Documentation Estate the Agent Can Defend
Every enterprise has the same documentation estate: an intranet nobody trusts, a wiki where the dev docs outrank the prod docs, crown-jewel recipes one bad...
