In this blog post, we will see how performance engineers can use advanced prompt engineering techniques to get sharper, more actionable results from LLMs, whether you are analyzing JMeter reports,…

Roshan: Wikipen [[File:{{#setmainimage:Example clickbait adverts.jpg}}|thumb|Fairly anti-memetic]] [[wikipedia:There Is No Antimemetics Division]] is a famous (in the subculture) book by…

Lauren Hall, Elizabeth Peel & Saul Albert Download transcripts | Keywords: Agency, Virtual Assistants, Participation, Footing, Technology How should we understand participation and agency in…

There’s much conversation right now about what AI can do. The processing power, the parameters, the emergent capabilities nobody fully understands yet. The question I keep asking: what does it enable…

A story about post-AI collaboration. An agent gets packed, sent through a portal, and arrives in a competitor's mirror to verify a claim. The walls hold. The work happens. Both go home better than…

GPT-5.6 Sol matters because the performance story is strong. OpenAI says Sol is its strongest cyber model yet . On ExploitBench , it says Sol is competitive with Claude Mythos Preview while using…

You might have been reading… Human scientist with AI support. (P/C Generated by Gemini Nanobanana with a long prompt.) …about all of the new tools people are building for online research purposes.…

Another thought leadership post about why teams should be smaller. I know, very original. But there’s a version of this conversation that’s actually useful, because the point is easy to…

In a recent podcast, Lambda (one of the neoclouds) CTO Stephen Balaban expressed almost bit of a disdain for the critics who wondered whether the hyperscalers or neoclouds are “gaming”…

To an increasingly authoritarian regime, the opportunity to shape how models describe the world may be too good to pass up on.

Andrew Nesbitt is a software engineer and package-management blogger who also writes excellent satire in the form of standardized industry documents, such as change logs and incident reports. I have…

I try to use the slot machines to solve code-related issues. For some tasks, these machines work well, for some tasks we get a long line of wiggle until it works but the wiggling does not produce…

I think Open source LLM's will hit a ceiling for this one reason: safety guardrails. Today we see Mythos and GPT 5.6 Sol put under heavy scrutiny for the primary reason that it is too unsafe to…

The brilliant content creator economist Matt Hill has posted a video “How Piracy Accidentally Created AI” to the @EconNerds channel on YouTube. The video is so funny (and smart!) that I…

Turning a manual into an agent's knowledge base isn't converting it to text — that flattens the thing that mattered. The power comes from the graph: the criteria that condition each other. How we…

Sovereignty has become one of the most common requirements in AI and digital procurement. The problem is that the word usually describes several different concerns at once.

Reading Time: < 1 minuteIf you’re using your weekends to learn AI, that’s not a bad thing. However, if your employees are having to use the weekends to learn AI because you’re…

Learning Creative Coding - HTML in Canvas - Plottimation Tool - Intro to Shader Programming - New Shader Playground - CVPR 2026 Art Gallery - Pretext - Hyperblam - AI and the Erosion of Programming…

This week I'm in Switzerland, at a retreat on the future of software development , in a room full of people who have thought about that future longer and harder than I have. I haven't come to…

Turning MetaHumans into Character Sheets with Gen-AI

Currently it is not feasible (for most people) to run frontier, state-of-the-art models (LLMs) locally. Data centers are needed to run these large models. However, I remain convinced that local LLMs…

You have certainly heard that, “you will be replaced by someone who uses AI.” It sounds logical. It may be the wrong bet. The most dangerous career advice circulating right now is this: learn AI…

Video

The typical language model is autoregressive (AR): it predicts one token at a time, left to right, each token conditioned on the ones before it. This bakes in two limitations: it cannot revise…

On the same stated cyber rationale, the Commerce Department pulled Anthropic's Fable 5 offline, the White House cleared OpenAI's GPT-5.6 for a chosen list of companies, and a second Commerce letter…

I ask AI to investigate my game's database instead of building dashboards. It changed how I think the end of SaaS plays out.

🔊 Listen to this post Tonight I found myself thinking about a comet. Not a metaphorical one. Halley’s Comet, the old celebrity of the sky, the bright visitor that swings through our neighborhood so…

Today's top 5 papers from arXiv covering AI, machine learning, NLP, and computer vision

The constraint that launched a thousand reasoning models may have just been optional.

null

In one month, the US government switched one frontier AI model off worldwide, rationed a second to about a hundred approved companies, and held a third back before launch. One government now decides…

How I achieved to ship code to production in the last two months without writing a single line of code by hand, with zero production incidents, zero rollbacks, and zero downtime.

The second wave of making my studio's work citable: AI installations and tools as research outputs, and the Zenodo metadata that keeps each record honest.

Hi, I know it's been a while since my last post. Things have been nuts in my personal life and I've also been hella busy at work onboarding someone new. I've just generally had a lot on my plate.…

How I run a solo AI consulting business from Slack: a fleet of single-purpose agents with the Claude tag as the meta-agent above them — reaching every surface, opening PRs, and maintaining the other…

I saw this at the bookstore and was intrigued by having a book that walks through the math of neural nets and machine learning. I have a very conflicted relationship with modern AI to say the least.…

Companies are halting graduate hires due to AI, and it's a mistake.

TL;DR Staying sharp in the LLM era isn’t nostalgia and it isn’t prompt-craft. The “agentic loop / context engineering” genre is largely a marketing story told by the parties…

AI memory systems are often designed as architectural bets: vector stores, profiles, summaries, graphs, etc. This post argues for a different starting point: build longitudinal eval environments…

AI gets you to a working draft fast. The trouble is what the missing fifth contains, the edge cases and operational reality that used to teach engineers their judgment, and who builds that muscle now.

My Vue MAD 2026 talk, written up. What an agent actually is, and the three things every Vue project needs to get more out of AI: context, feedback loops, and discoverability. The twist is that none…

Two weeks ago, someone posted an internal proposal: My dream for the future is a good proxy that automatically sends requests to the most appropriate model, allowing us to run a heterogeneous AI…

Current-generation AIs are particularly good at finding and generating corresponding patterns. This can be useful when classifying images as cats or dogs (classifiers) or creating new sentences or…

The default assumption should be that foreign state actors have already exfiltrated the weights of Claude Fable 5 and GPT 5.6 Sol, the latest frontier models from Anthropic and OpenAI. Here’s…

The honest math on building your own AI box in June 2026, who it actually makes sense for, and why timing matters more than people think.

In January of this year, the Conference Board of Canada, now Signal49 Research, projected that 555,000 jobs in Canada would disappear by 2030 because of the widespread adoption of artificial…

When I say AI is too expensive normal people tend to look at me like I'm crazy. ChatGPT has a pretty generous free tier. For those who choose to pay, $20/mo gets you essentially unlimited AI for…

Some personal hot takes from AI: Engineer Miami follows...1. Software development is a dead-end profession because anyone can be a software developer now. 2. Anyone can use Cursor or any other tool…

Reasonable people

AI approval gates: reversibility-tiered human-in-the-loop design with four health metrics that prevent reviewer atrophy at machine speed.