Les Orchard <me@lmorchard.com>

The Open Source Web Agent Evaluation Framework

Finally, an online ‘cyberpunk’ game that comes close to portraying computing as depicted in classic cyberpunk works like Neuromancer by William Gibson. In this game the player is a NetRunner, an arrogant and bold futuristic hacker. Armed with his cyberdeck and an arsenal of offensive, defensive and analysis software he’s ready to invade corporate systems in the grid and raid their credits, for fame and fortune! It’s no cakewalk though! Waiting for the unwary are Intrusion Counter-measures (IC). Machine controlled defenses that can inflict damage to hardware and software, steal the players own credits and even cause… death.

The metric we killed is back, and AI made it worse

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

I recently purchased an Amiga 1200 which has hard drive support through an internal IDE connector. Adding a hard drive is appealing since booting from floppy disk or a Gotek floppy drive emulator can be quite tedious and slow. The good news is that there are solid state options using compact flash (CF) or secure digital (SD) card solutions through an IDE adapter. I went with a CF card adapter that I purchased for less than $30 from AmiKit on eBay. This is shown below inserted into the IDE slot on my 1200.

Based on conversations with study participants, we believe it is likely that developers are more sped up from AI tools now — in early 2026 — compared to our estimates from early 2025. However, because of the selection effects in our experiment, our data is only very weak evidence for the size of this increase. Our raw results show some evidence for speedup. Our early 2025 study found the use of AI causes tasks to take 19% longer, with a confidence interval between +2% and +39%. For the subset of the original developers who participated in the later study, we now estimate a speedup of -18% with a confidence interval between -38% and +9%. Among newly-recruited developers the estimated speedup is -4%, with a confidence interval between -15% and +9%.

Introducing Times New Resistance – a Times New Roman impersonator that autocorrects the autocrats. Do you have access to the computer of an ICE apologist, white supremacist, Republican mouthpiece, right wing propagandist, or other morally bankrupt American? Install Times New Resistance and unleash some mischief.

For Anthropic’s stated goal of demonstrating that Claude can build complex software, CCC is a genuine success. For anyone wanting to compile software to actually run efficiently, GCC (or Clang, or any production compiler) remains the only real option.

Imagine you have two machines. One you can open up and examine all of its workings, and if you give it every picture of a cat on the whole internet, it can reliably distinguish cats from non-cats. The other is a black box and it can also reliably distinguish cats from non-cats if you give it half a dozen pictures of cats, some apple sauce, and a hug. These machines sort of do the same thing, but even without knowing how the second one works I am extremely confident in saying it doesn’t work the same way as the first one.

I’ve been working on developing an operating system for the TI-99 for the last 18 months or so. I didn’t intend this—my original plan was to develop enough of the standard C libraries to help with writing cartridge-based and EA5 programs. But that trek led me quickly towards developing an OS. As Unix is by far my preferred OS, this OS is an approximation. Developing an OS within the resources available, particularly the RAM, has been challenging, but also surprisingly doable.

I don’t think we will ever go back to how we used to program. And it happened so fast that I didn’t even notice when it happened. One day I was writing code. The next day I was… still writing code, but with AI. And then at some point it flipped. Now I’m mostly directing code. Reviewing. Prompting. Iterating. The AI writes most of it. It wasn’t a dramatic shift. It was subtle. A little bit more capable every week. And suddenly I’m here, doing the dishes, realizing that everything has changed and I don’t know exactly when.