• Went out earlier with the intention of getting a few things fixed, but didn't manage to get any of them done. Still to do

  • Put air in the tires

  • Get the gas & heating working

  • Get covers for the windows

• • Snack: Yogurt & Granola

  • Lunch: Khan's Meal

• Quite happy with how this week went. 4 days ago I wrote Health 2026, and because I kept it simple, I remained focused on it throughout the week. Previously a common failure mode has been "I'm not sure if this fits within my guidelines, fuck it I'll eat it so", but because I have a clear guideline for eating out and snacking, that didn't happen this week. Let's see if it continues this week.

• The Van Cheat Sheet

• Gas

  • There's a huge red gas canister below the van on the driver side. There is some way to turn the gas on or off from that canister itself - you have to lie down on the outside of the van.

  • In addition to that, there are three knobs under the sink that control the flow of gas. I believe one of them is for the fridge, the other is for the hob, and the other is for the heating.

• List

  • Breakfast: Yogurt & Granola, no chocolate

  • Snacks: 2x small slices of pizza

  • Evening: 10x salted crackers, assorted cheeses. Likely around 1400 cals

• Hospital experience today was a reminder of why I love Amsterdam. It was a 5 minute drive, everyone we dealt with was competent, thorough, and good at communicating - it's remarkable how consistent this is across the Dutch population. The queue in front of us was 3 people, maybe a 20 minute wait, less for the second appointment. Just an all-round painless experience.

• Set up sentry alerts to the internal_scout channel

• Wasn't happy with the name streak.fyi. Landed on "updates" as something descriptive enough, bought updates.fm and transferred everything over.

• Nov 27 checkpoint

• I feel like we've hit potentially the first "product-is-good-enough-for-x" point since we started. You can now Sign in to scout, sign in to your services, and ask Scout to do stuff within those services, and each of those steps works reasonably reliably.

• Next Tasks

  • Going methodically through the list of services like a checklist and documenting the extent to which they work & issues like screen sizing.

  • For services that need desktop, don't have a 50/50 grid - instead switch to 75/25 split

• Other Learnings

  • Smooth isn't good at summarization tasks, it seems trained to be very utilitarian. For example if you ask it to summarize all the conversations, it will just give you back the raw transcripts, even if you prompt it to summarize. It will say things like "Action Items: ..." and then just repeat the raw messages. We have a few options to address this: 1. Parse the returned output with a different LLM. 2. Tell people to use hyperbrowser for summarization tasks, 3. Add a router ourselves which would check what kind of task it is and route to Hyperbrowser if summarization, or 4. Tell people for now not to use it for summarization.

  • The "Skills first" approach feels less natural when I'm attempting to use the product each day. I find myself just selecting free text mode and then typing out the full url of the service. I'm wonder if it'd be better to simply allow people to @-mention services

• Did a call with Luca & Antonio to try to get to the bottom of the iframe typing issue. Couldn't get anywhere but concluded it's probably just my machine.

• List

  • Lunch: Soup (Brocolli, onion) & Sandwich (Chicken & rocket) on small ciabatta

  • Dinner: Khan's chicken & Rice

  • Snack: Natural Yogurt, honey, Holies granola, half bar of Tony's chocolate

  • 

• • Lunch: Khan's chicken & rice

  • Dinner: Cheese burger with sauces, handful of fries

  • Snack: Natural Yogurt, honey, Holies granola, half bar of Tony's chocolate

  • Other: Tea, Powerade

  • 

• Call with Megan Raf Niel to plan client app migration

• Call with Christian to debug App performance issues - link

• Continued adding changes from yesterday. Better font & added a top bar, still have more changes I want to make though.

• Call with Ahuva. Went through the tickets and docs but didn't manage to get anything agreed, and ran out of time. I told her I'd follow up with more, but it's 6:30 now and I haven't got to it. She emailed asking to chat, will have to be tomorrow.

• Did team call. Notes left in Asana. Todo for me: Code review the massive Pull Request

• Terrible day today. Got to the cinema late so didn't get to Albert Heijn. Next time 100%

  • Lunch: 2 longganisa sausages w brown rice. 550 calories.

  • Cinema: Large nachos & 2x cheese dips: 1800 calories

• The Extinction Scenario

• This is more of a brain dump of random strands of thought than an article-that-makes-a-point.

• Premise: There's a lot of talk of "AI doom" - a scenario where an AI is created, that wipes out humans, either through malevolence or by-accident-when-given-a-goal.

• Background Ideas

• The Destruction Equation

• Humans are pretty well distributed around the planet. In any scenario where all humans get wiped out, there are three things that would be needed.

• 

  • The word "Bomb" in this diagram is can be taken to mean "anything that can wipe out all humans". Currently in this category we have state owned nuclear arsenal and advanced bioweapons.

  • Accessibility of the trigger: How easy is it for someone to access, for example a bioweapon or a state's nuclear codes.

  • Forcefulness of the human: How much will does the person have to follow through. If the trigger is accessible enough, all it would take is someone having a bad day. If the trigger is extremely protected, it would take enormous effort, organization and co-ordination to access it.

• If the question is whether an AI can trigger this, we can replace "Human" with "Agent", which in this case means an entity with agency and intelligence.

• 

• The Forcefulness Equation

• Zooming in further on the left side, in order for an entity to successfully trigger catastrophe, they would need to

  • Reach a conclusion that they should trigger it (likely with some underpinning theory of why).

  • Figure out how they could trigger it

  • Remain in an observe-narrate-act loop for long enough to undertake all of the actions required (avoid being "shut off")

• A model is not an ego-centric brain

• How Easy Is It To Destroy all of Humanity?

• This is an exploration of the likelihood of AI extincting humans and an add-on to this article: The Extinction Scenario

• Check in: I'm not doing great on this stream at all. I haven't been tracking what I'm consuming, and haven't been making smart decisions. Need to get back on the wagon.

• Health 2026

• My biggest issue historically has been lack of consistency, most of which has been life-distraction related. I'll decide to take it serious, start doing the stuff, then we'll go on a trip and get out of routine, come back, and I'll completely forget. The good news is that over the last few years I've built up some approaches that don't feel super difficult to adhere to, which I can return to.

• What I know

• My daily meal types can be broken down into 3 categories. Here are the heuristics for each:

  • Snacking: Make sure we're stocked with the right groceries.

  • Eating Out: Order small low calorie meals - soup, sides etc. Eat dinner at home

  • Dinner: Eat Khan's Kitchen meals

• Daily Goals

  • 150g protein

  • Little-to-no processed foods

  • Rough calorie calculation each day

  • No food after 5 (for better sleep)

• Weekly Goals

  • Do groceries at start of week

  • Exercise 3x/week

• Side Notes

  • Diet soda is allowed

  • Food idea catalog is here.

• Chat with Earle: Let's interview more people & keep high throughput to the exercise, goal for having someone on is Dec 10. Todo: Add to github and weave

• Chat with Patrick: Gave update on all streams & clarified intent to continue with same commercials

12:45

• Added a bunch of features

  • Domain set up (Streak.fyi)

  • Add Stream Groups

  • Clean up all my old streams

  • Clean out Roam so that postman is fully set up

• Updates

  • Added integrations page.

  • Got provider switching super clean/bug free.

  • Lots of feedback back/forth with Smooth team.

• Week 48

• Tuesday: Conversation with Faith about where to focus. I'd like to venture more into paid ads as they're more predictable than our creators

• Several updates last week & this wk: Improvements to how components are managed. Website udpates. Oh and we integrated htm from preact so we can use it for templating in components.

• Made lots of changes - finally got groups (channels) sorted and began. Feels like I almost have the "life dashboard" I'd been envisioning.

• Nov 24: Really feel like I'm missing out on saving great content, so I went and fixed the Chrome extension. It's now working for me, but it's still not published on the Chrome Extension Store. To return to this

• Streams this week

  • 24 Tax return: Ieke responded about the updated return with the overseas holding companies included. Return now submitted

  • 24 Irish Returns: Got docs signed & Emma submitted both Fuse & Tonic returns to CRO.

• Week 48

• Monday: Got response on our offer for Prinsengracht & it was a rejection. Super bummed out. Called them - they chose another family because of both offer amount and their profile. Learning: next time bid higher & include a letter.

• Tuesday: Viewed place beside Volkshotel - lovely with high ceilings but not enough rooms. Told the agent we were looking and he said he'd send on another place near Vondelpark that's not on market yet & is much bigger

• Week 48

• Monday: Got response on our offer for Prinsengracht & it was a rejection. Super bummed out. Called them - they chose another family because of both offer amount and their profile. Learning: next time bid higher & include a letter.

• Tuesday: Viewed place beside Volkshotel - lovely with high ceilings but not enough rooms. Told the agent we were looking and he said he'd send on another place near Vondelpark that's not on market yet & is much bigger