Weryj

How are we supposed to keep up with the sheer volume of cool note-worthy tools coming out. This is getting out of hand

It doesn't matter if the model is good. Antigravity cli is unworkable, I thought auto permissions was a solved problem by now. I can't keep sitting here to press allow when in auto mode.

I think it’s more like ‘The absolute maximum possible degree of theft’ there can’t be larger, it’s everything current and past.

Not necessarily. ADHD is at the neurotransmitter level or density of receptors. Which could be an epigenetic condition from prenatal environment.

Or maybe it’s learnt like you say, I think both areas would be worthy of researching.

I work in grid management, and the Telemetry from EVs is a valuable data stream for steerable demand on the grid, a genuine societal benefit.

The only data we need is if you’re at home and the charging metrics /w commands.

But the amount of unnecessary data that is available, is a real privacy concern.

Nope, OpenAI partnered with Broadcom to produce their own chips and the performance/watt looks good

Could also frame it as, the OpenAI agent civilizations (from hugging face attack) are looking for the failsafe.

I agree, stress during pregnancy could also be a signal shared with the developing brain.

I don’t mean from a nutritional standpoint, but a behavioural perspective. Smaller groups would have an higher percentage of responsibility per individual to be vigilant and proactive.

It would make sense to me that evolutionary there would be different mental development paths depending on the requirements of their situation.

This is coming from my understanding that ADHD is more prevalent in stressful upbringings.

I’ve always thought, it’s not absurd to think there different development routes which the brain takes depending on the environment it develops in.

With your foraging example, it does make me think ADHD is a small group/individual optimisation. Prioritising high vigilance and individual productivity over social cohesion.

I speak with no authority. I don’t even know how such a theory could be tested.

That's probably because they want to develop cross-platform.

The Netherlands sells 500x0.1mg pills, so you can always get the perfect dose.

Wasn’t quite right before, but Optane was sold off, so it’s sad the buyer just sat on the IP.

Also the selling point was latency, but I suspect we’ll see bandwidth being the important metric with AI using deep pipelines to stream in the weights in a latency insensitive manner.

There's a famous son of a star, his fame comes from drug addiction and felonies. I'm doomed to have this bias on my name forever...

Wait, did that need a /s?

I think this was the most sensible way to deploy this model. Considering how much of a step up it has been from Opus.

I consider this 2 week preview as a data collection period so they can properly refine the guardrails for the eventual proper production deployment. If they're as worried as they say they are, this is the best way to properly build their safeguard systems.

It's annoying af, but I'd rather be cautious here.

If only there was a way to download e-books and upload them to a Kindle with Calibre.

Because it forced them to focus on efficiency, instead of throwing more compute at the problem.

Just like in software, some of the most beautiful solutions come from constraints. Think, the optimisations that game developers implemented because of the frame budget.

Actually there’s a change to dotnet 9 with how it handles the heap and GC which caused major issues for us.

I’ll confess the reason it hit us so hard is because the code quality was so low and wasteful on allocations that it didn’t hide the problem as well as previous versions.

Insert photo of Simpsons drinking bird while homer sleeps here.

My monolith is large enough to work on multiple systems in parallel without overlapping. One prompt with Opus might take 30-40 minutes once past the planning phase.

So I plan the next work, while the current is still running and if that's a task that can't have parallel work, I have a bunch of time to keep planning the next steps for other systems.

And then there's time for reading through the changes and applying corrective changes to the code or the meta-skills.

I use CMUX and setup workspaces for each topic I'm working on, each workspace has number of tabs. That helps keeping track of everything I'm working on, but also means no topic gets left behind until I close the workspace. So they accumulate

I was generalising a bit, but in a way where only a subset would agree. It's all anecdotal and very personal.

That was the first thing I did, it still recreated it. Surprisingly

But maybe that was a me error and worth a second shot.

This, the vm bundle which reappears after you delete it. They say it's For Cowork and Claude Code, but if you don't use Cowork or CC sandboxing, it has no value. Considering I'm always finding things to delete on apples anaemic 512gb because I run out of space.

And Claude is hogging 12G for Cowork which I don’t want.

I thought about it a little deeper and I think software development has always had the addictive tendency. That hunt for the solution to the problem, has a rush when you complete it.

It’s just that the rush is more frequent, addiction intensity scales with dose and frequency.

I could have written this article myself.

The addiction part, the ADHD part and the pending test part.

The fear of becoming addicted to AI is real and I don't think I'll be capable to stop it, considering we're asking people who struggle with avoiding quick dopamine to use it professionally in their daily work life.

My Pro went to Max(5) to Max(20) pretty quickly and I was burning through that weekly limit still, without large agentic workflows that burn tokens. Just me and 4-5 terminals. Sometimes I was happy to hit the limit because I was forced back to normal life.

I've gone back to Pro to stop what was happening.

Now I'm self-aware enough to notice the trend and put up safe guards, but that's because I've always had to adapt my environment to control my behaviour because I know direct behaviour control is abnormally challenging. I fear for those who won't see it coming, until they're in deep.

Pure agentic loops with markdown documents as a program 'agentic workflow' is incredible for experimentation, developing and testing your workflow idea.

The second it works, bake the workflow into the harness. Yesterday I was doing just that, and the whole agent loop disappeared because the process could've been condensed into a one-shot request (+1 MorphLLM fast apply) from careful context construction. (It was an Autoresearcher)

I brought this up during our AI workshops, but I called it the “confident idiot”

Seeing the idea explored in such depth is great, I really am concerned about this.

It’s that I try and then can’t. When stuck in bed I can feel this momentum building in my head to push for movement and the a surge of will and then nothing. I didn’t reach the threshold of exerting my will and now I’m waiting for the next wave.

Guess we’ll see how my diagnosis goes.