_puk

Cowork gets tangled with git as well. Fails, and then can't delete lock files.

Running a helper from the terminal, making Claude work in a working directory, and then create a .commit file has been my workaround for this for a while now.

Imagine there's a better solution nowadays, but this allows me to use dispatch building on Vercel, so I can check it out from wherever, without too much pain.

The American industrial revolution is often cited as one such example.

The patent act of 1793 is still relevant today [0] and was established to protect Americans stealing British and European industrial trade secrets.

https://mysteriesofmankind.com/industrial-espionage-the-spie...

https://neo.gsfc.nasa.gov/servlet/RenderData?si=2050444&cs=r...

Direct link

I have a lot of thoughts on this, I should start writing a bit more publicly.

I'll be watching closely, we're moving this way very quickly. If you get there it'll save me a job!

One thought, the knowledge graph rowboat creates is passive, based on context in emails, transcripts etc. A tool to pull further context from an individual would be amazing. Sit there and chat with it to flush out all of the tribal knowledge (gotchas in this spec).

We have Context Capsules running in production as agent context (amongst other layers of governance) to define metrics etc, so we can guarantee what you see in your dashboard matches exactly what your invoice says, what we're reporting externally, regardless of who is reporting it. Agent or human.

The format is:

https://contextcapsules.com/v2/CONTEXT_CAPSULES.md

Context Capsules cover business concepts (even org structure), all the way through to implementation. Compounding value from bounded context.

I implemented the Granola Sync when rowboat stopped pulling it in (I have a year's worth of transcripts of pretty much every conversation I've had over the past year).

One shot granola sync in both TypeScript and go from a single Context Capsule:

https://downkeep.com/sDzvgoKx/granola-sync?k=bJ0JXOTErCt1XVU...

Nightmare passing markdown files around in this day and age, and yet they are the future. DownKeep is my personal attempt at keeping some sanity, not production!

Tenda has been around for quite a few years now. I don't imagine they'll rebrand.

I have an ethernet over power adapter somewhere in a cupboard from perhaps 10 years ago.

Back then it was standard for the admin password to be 'admin'. They'd often even print it on the device itself.

I actually was using this quite a lot earlier this year, thanks for this!

What I actually ended up doing was regularly pointing Claude at the Rowboat directory. Really useful to have all of this context available as markdown files.

I use my own standard format for all context capsules, and had my own branch running with that format hacked in.

Being able to describe the format in a plugin style architecture would be awesome.

Granola notes silently stopped working when they decided to encrypt the DB, interesting to see you've got your own in there now.

Will check it out again.

Love it. Especially the fact you got it physically running on the M5 stack.

My mind immediately went the other way though - feeding it to stop it evolving into the even worse next iteration of itself. Feels like that's where we are right now in the real world! Keep it distracted!

Don't bite. You're right.

Having spent a good weekend learning how to perform latent-steering through playing with pytorch and a local Gemma4 model, there is no way I could have groked any of that in the the way I did without hands on time.

This is on an M3 Max 36GB I've had for a couple of years. No further outlay needed.

Quite the sweeping statement that contradicts my recent time across a few European countries.

If the primary purpose is a bar that also serves food, yes.

If it's proper dining. No

But renting is a problem if there's no asset at the end of it.

Even if rents were capped at half what a mortgage for the same property is, you still are in a position that once the asset of the house is paid off the landlord now has an asset that earns income without labour.

And the inverse.

Regardless of what you earn (to a point, even into higher income brackets), if you do not put it into an asset that can house you, and you stop earning, you cannot live without reducing your overall capital.

So rental means a lack of opportunity to reduce your labour dependent income over time (important as you age), and a reduced ability to weather negative life events.

So Bedrock 4.6 is old school Opus?

I know you can point Claude code at Bedrock.. might be worth a play.

This hits a sweet spot I think for conversations too. I've been playing (for quite a while) on trying to encapsulate long running conversations.

You have the overriding context, facts that don't change very often at all. The participants names, their backgrounds etc.

Then you have some very fine grained facts (what they ate for breakfast this morning) which might be useful right now, but are irrelevant outside of a general trend over the longer term.

When trying to reconstruct a conversation you really need to find the right balance without pulling in everything that has ever been discussed.

This definitely is worth further investigation.

It's a play on "in space no-one can hear you scream", not a literal "compute is so noisy we need to go to space"

The jurisdiction issue is the bigger one. Deserts don't solve this; International waters, possibly do, but then you've got other issues.

Never before has the adage "if I took* more time I would have written less" been true.

*Yes, I know

Here's a massive document, without any real context as to what thinking went into the points it's making, tell me if it looks ok. Oh, and there's 10 more where that came from.

We're outsourcing the thinking to the recipient.

Yes, it's way easier to create the report now, but it's not being honed down to the crux of the points it needs to make. And the reviewers are expected to what? Up their ability to mentally consume and reason about reports.

I mean, barrier number 1: did you read it yourself before asking someone else seems too high for some..

That doesn't have the Gemma models by the looks

Just do a VW and detect when you might be in the testing phase. Off the top of my head:

Train it dumb on "systems:, user:" prompt pairs.

Unleash on "system:, user:" prompt pairs.

Guess which you're providing for evaluation.

Yeah, it's still useful to refer to patterns.

Facades and stranglers are massively useful patterns, and help explain concepts to the layman.

Personally I've never been patterns over everything, so I'm not going to now knee jerk and say no patterns ever.

There's a time and a place for everything.

edit Fuck. A reread on that and I sound like AI. Updated

Part of the problem: you get given a complete document to review after it's been fully baked.

I'm pushing the need for basic engineering principles across whole organisations.

You wouldn't give an engineer 1000 lines of code to review without the original spec of what you're trying to achieve for context (at a minimum, ideally the reviewer was in the room when the work was introduced, and has full context).

So, these docs, they're given as an all or nothing.

Do you push back on the 39th metric that is defined to the utmost detail? Or just resign yourself to the fact that it is what it is?

A one (6 is the goto if we're talking Amazon?!) pager.. "this is what I am proposing" at least gives the skeleton of the idea to push back at the general shape of the idea, refine it, before all the emotional investment of your precious report being complete.

Y'know.. the traditional product running through the spec in a SCRUM* environment.. the engineers doing proper code reviews..

* Yes SCRUM is dead, but that's another thing.

And 4.7 is so last week..

2024. Oh woe, I have to scrape everything, why don't companies just give me an API to consume what I need.

2026. Oh woe, the MCP that all the companies are giving me isn't ideal.

2028? oh woe, the CLI that calls the REST API, that calls the MCP that all the companies are giving me..

Exactly where my head is at.

Not only do you need to spec everything to the right level of detail (at which point an LLM can likely make a good go of it), but a lot of the outsourced teams don't build in anywhere near the same way as those internally, and the difference in the level and speed of delivery is absolute.

Not to mention with everything changing so quickly, why would I be spending time and money training up someone else's staff to be keeping up with the cutting edge?

45 seconds of didge, and then be puts it down!

Hope he sleeps well tonight!

Lol. Young uns!

Flash, ah, ah, saviour of the universe. Flash, ah, ah, he'll save every one of us!

Every time I have heard the word flash for goodness knows how many years.

I couldn't imagine using CC on the basic tier!

Even operations and GTM are all at "professional" level (which I think is vaguely equivalent to 5x).

I think Opus 4.6 at its peak was the "how can anyone not get that this is good" for me.

Then the nerf, and the massive uplift in tokens for 4.7, a model which I find lazy and prone to hallucinate.

It's probably time to try GPT5.5. Like many I'm pretty heavily invested in the anthropic ecosystem at this point, which I suppose gives another strong reason to make the switch.

So maybe the AI labs have been paying attention after all!

I think this mainly demonstrates that the pelican on the bicycle has firmly exceeded its limits as a useful benchmark.

As acknowledged in the article.

25 years ago, we were still trying to milk as much as possible out of autoexec.bat and config.sys.. maybe we'd moved on slightly, but we were definitely still trying to get the damn 56k modem to give us the best ping possible.

All this to say.. it was fun because it wasn't easy. We were learning.