paulbjensen

If the goal is to maximise the utilisation of RAM in devices for computation purposes, then there might be some value in exploring these items:

- https://github.com/exo-explore/exo - https://machinelearning.apple.com/research/distributed-gpu-c...

I had no idea he played Karla in TTSS, but very familiar with TNG, the X-Men films and his turn as Gurney Halleck in David Lynch's Dune.

RIP

Dreamhost - gosh that brings back memories…

I watched "Enron: The smartest guys in the room" documentary, and I think Lou Pai is the most fascinating character in the story.

As quoted online:

Lou Pai was a senior executive at Enron who, after having an affair with a stripper, to satisfy his divorce settlement, cashed out $250 million of his Enron stock just before the company's stock price collapsed and it filed for bankruptcy protection.

I don't know if he ever knew about the stuff that was going down at Enron, but that guy managed to leave the ship in a nice boat before it sank.

AI models with worm/virus-like capabilities.

Reminds me of that scene in Chernobyl where Mikhail Gorbachev reacts to Valery Legasov explaining how melted uranium reacted with dropped sand:

"You have made lava?"

He was great in Breaking Bad.

It was one of the things I appreciated about BB - how many tv shows would cast someone with Cerebral Palsy in it? It made the show feel more genuine and realistic, along with being set in a place in America that isn't a well-known location.

I'm sad and angered to learn that his manager committed fraud with his tax payments - I hope the authorities pursue her and hold her accountable for that.

...I've an idea for the rest of where Copilot is used.

freeze-in-hell.bat man!

https://www.getyarn.io/yarn-clip/0def6aed-0b5b-4856-874a-d97...

He who controls the Slack, controls the (Wordpress) universe.

I helped do the video recording and the website for the 2013 International Forum on Quality & Safety in healthcare that was held in London at the Excel Center.

One of the talks there was from Qantas Senior Check Captain David Evans, "Teamwork Under Duress" there, which was all about that flight and what happened.

It was an amazing talk, and I have a huge amount of respect for the job that airline pilots do.

I was using this model: https://huggingface.co/unsloth/Qwen3.8-27B-GGUF

Quantization is Q4_K_M (4-bit K-quants, medium)

From Pi, these are the up/down token counts:

Tokens: ↑147k ↓110k R26.5M

Prompt submitted at 18:52:54 BST on Sunday 16th August 2026, and finished at 04:05:27 BST on Monday 17th August 2026.

Last print out from the llama.cpp server logs:

881.42.815.480 I slot print_timing: id 2 | task 110233 | prompt eval time = 2742435.76 ms / 134911 tokens ( 20.33 ms per token, 49.19 tokens per second) 881.42.815.483 I slot print_timing: id 2 | task 110233 | eval time = 6312248.28 ms / 5804 tokens ( 1087.57 ms per token, 0.92 tokens per second) 881.42.815.483 I slot print_timing: id 2 | task 110233 | total time = 9054684.04 ms / 140715 tokens 881.42.815.484 I slot print_timing: id 2 | task 110233 | graphs reused = 114795 881.42.820.381 I slot release: id 2 | task 110233 | stop processing: n_tokens = 140714, truncated = 0

I just used it on a Apple M4 MacBook Pro with 48GB RAM with llama.cpp and Pi to help diagnose an infinite looping request in a React Server component on a Next.js application.

After about 10+ hours of digging, it has apparently found a bug in the Next.js framework, with an example app that replicates the bug, and a fix for now to disable prefetch in the Link component.

I had in my prompt asked it to discover the root cause of the bug and propose a fix, but I did not expect it to dig this deep.

That was a great read.

It's only a matter of time before there are sponsors on the Yellow and Red cards...

AWS revenue for 2025 was $128.7 billion, so I'd say probably a bug.

Fantastic, this is brilliant.

I have tried to cancel a newspaper subscription in the UK a few times, which is only possible by telephone, and they have a serious churn-reduction program in place where I end up getting a major discount on the subscription.

> Our hypothesis is simple: session logs are now the most important artifact in software development, and should be stored alongside the code itself in the repository.

Pi.dev has a feature where you can export the session as a html file and look at it later. I foresee that potentially you could store this in the same Git repository and get the benefit of reviewing how a particular code change came about during a session with an agent.

I guess the next step would be having the coding agent save that session context automatically in a folder in the git repository rather than requiring a human to export it.

This startup also seems to be operating in a similar space to tangled.org - moving code repos into a decentralised hosting environment.

I’m talking about CI pipelines where you have:

- Unit tests - End to End testing with Cucumber and Puppeteer (or Playwright these days) - Code Coverage analysis - Lint and formatting checks - Tools like knit to remove unused code - Security checking tools like Synk and Socket - Size checking

If you look at what those tools do, they automate aspects of reviewing PRs. The question then becomes - what still gets done manually, and are there ways to automate that.

Meditation is great, but there might also be other options available when it comes to dealing with the effects of context switching.

For me, I find the Pomodoro technique really effective, but there's a key caveat, which is that you try to focus on one thing at a time (which flies in the face of using multiple AI agents working on x number of things at the same time).

Another angle to explore is how much of the process of software development that we do manually can we automate, particularly the parts that still require human input (like code reviews). That may also help with reducing the cognitive load.

Update: Running this in the terminal works:

sudo pmset -a disablesleep 1

And if you want to revert that, run this:

sudo pmset -a disablesleep 0

I've just run into this issue. At first I thought that there was something wrong with the cable or the power, but now stumbled on this thread.

Laptop: 13" MacBook Pro, M1 processor, 2020 edition Display: Apple Studio Display

Once more onto the breach…

Actually, this would be amazing for distributing web games as apps for Steam or online purchase. I am going to give it a try.

Great game, loved taking a peak behind the scenes and seeing it was using HTML5 canvas.

Will buy the game later on, especially as it's only $5 - I guess that's a latte in the US these days?

Recently I got AI to help make a script to convert a CSV dump of trading activity on a trading platform for uploading into another stock trading analysis platform.

Later on, I managed to crunch the numbers in the script, and realised I could dump them out and display them in a dashboard alongside the trade activity. So I built that too,

An excel spreadsheet could have done the same job as the dashboard, but the script for conversion was greatly aided by the AI tool. The work otherwise would have been a bit of manual coding and back-and-forth testing.

I find it nuts that I can use Claude Code for $20pm - I imagine that won't last forever but have to say it is great value for money.

So when I see monthly budgets in the thousands for developers at some larger companies, I'm curious to learn how they are managing to spend that kind of figure: how much code/documentation are they feeding into their prompts, are they using agent orchestration systems to make the code factory run 24/7, and how much value is coming out the other end versus before?

And, if they are pouring thousands into LLMs per developer, have they considered looking at alternatives like having LLMs running locally on own hardware with their own agent harness?

Those are the kind of questions I'd love to ask - I just wonder how much stuff is truly cutting edge and how much might be wasteful?

I would say the first time I did “vibe coding”, when I tried Claude Code with Zed’s agent integration in January this year.

I wanted to see if I could build an image editor for isometric graphics using HTML5 canvas, Svelte, Vite, and the. Rather than do all of the skeleton code setup, I figured “why not try and see if Claude can build the app scaffolding?”.

I gave it a prompt and watched it produce the scaffold, along with a few features I outlined in the prompt.

When I booted the app and saw that the features worked and that there had been an element of design to the layout, that was my mind-blown moment. In a period of about 45 minutes, I added some features and had a basic MVP at the end. I walked back home stunned.

That app is available for free at https://babspixel.com

Anyone who deletes Microsoft Teams deserves a raise.

Looks like RedHat got compromised by a Black Hat…