Kris Cruickshank

[Massimo @Rainmaker1973]

When you have a bad day at work but you don't smoke.

[Greg Jackson @g__j]

Fatih Birol, boss of International Energy Agency:

“Electric cars are now - worldwide - 30% of new car sales. Five years ago, it was 5%”

It’s why fossil fuel lobbyists are so relentless right now. EVs are increasingly cheaper to buy, cheaper to fuel, cheaper to service and better to drive.

“15 years ago solar was a romantic story. Now it is everywhere… wind and nuclear will make a big contribution as well”

If you look outside the UK, these changes are everywhere and huge

[Science girl @sciencegirl]

The fountain that shows date and time.

Czech Republic.

[Sarah Go Green💚 @sarah_go_green]

So the day has come and @OctopusEnergy has changed their rates. These are now live on their website.

The new offpeak rate on IOG for NEW switches will increase to 7.5p per kWh and for GO 9p per kWh.

There will be a 6 hours limit of offpeak from your vehicle each night BUT this won't start until around mid March for everyone.

@agile_phil confirmed they are working on the app and the changes won't be in place by St David's day so the 6 hour limit is on hold for now.

BUT possibly by mid March there will be a slider which will easily allow customers to limit their charge to 6 hours max.

It is at this point the new rules will come into effect.
(The house still gets offpeak too)

The slider will give reassurance customers won't accidentally charge at full price unless they want to.

You'll be in control and can decide if you need to go over 6 hours.

I think it's amazing they've listened to feedback on this!! It feel reassured i can still use IOG as intended now!

There's slightly more to come on another tariff. I know a few of you will be interested in this one too but you'll need to standby for that.

RECAP

So if you are already on Go or Intelligent Go your offpeak rates will stay the same and NO 6 hour limit of offpeak for the vehicle is in place yet. That'll be maybe Mid March and the app will have a slider to limit the charge time to 6 hours if needs be.

[mitsuri @0xmitsurii]

How was the show Silicon Valley so ahead of its time?

[Kris Cruickshank @KristopherTC]

@JJackBrandt Not to mention the accident that would have happened if driving a normal car.

[Planet Of Memes @PlanetOfMemes]

When the Testers aren't using the product as intended.

[Kris Cruickshank @KristopherTC]

@DirtyTesLa If it was such a problem for you, why didn’t you do something about it like this guy: https://t.co/ePU0pLeMrQ
😉😜

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Kris Cruickshank @KristopherTC]

@DirtyTesLa @SawyerMerritt @Tesla I agree. I actually think it maybe it should be tiered: mileage based. I don’t drive a lot. So not willing to pay much.

[NASA @NASA]

Today, Jared Isaacman (@NASAAdmin) was sworn in as NASA’s 15th Administrator. At a time of intense competition across the last frontier, he will lead the most talented minds in the nation to ignite the orbital economy, usher in world-changing scientific discovery, and return American astronauts to the Moon – this time, to stay.

America’s historic mission in space continues. 🚀 https://t.co/zbSZLTZFiv

[Kris Cruickshank @KristopherTC]

@docm77 lol

[Kris Cruickshank @KristopherTC]

@WorldofKeralis I like the shaders you are using what are they called? Also your build is soo impressive!

[Joe Tegtmeyer 🚀 🤠🛸😎 @JoeTegtmeyer]

Not sure which was worse, the robot falling and shattering into several pieces or the guy trying to pull the black curtain to hide the carnage. 😳

[Kris Cruickshank @KristopherTC]

More #Aurora shots

[Kris Cruickshank @KristopherTC]

The #Aurora in #Edinburgh tonight is amazing! So strong I could even see it clearly with my eye (previously I needed the camera)

[Kris Cruickshank @KristopherTC]

1) improved Tesla vision parking mode when going slow and close to objects. Tight carparks and drive thru is nerve racking with out seeing objects.

2) directional audio for how close different objects are to the car. I want to be able to park with my ears (it was probably the only Toyota feature I miss)

3) something like Fsd speed profile and traffic understanding in free autopilot world wide. Autopilot can be quite dangerous because of these things in uk. Still pay for full fsd, just need road understanding from fsd.

[Kris Cruickshank @KristopherTC]

@GeminiTayMC Getting back into Minecraft while watching Hermitcraft 11?
I made a handy Modrinth Modpack Upgrade tool that helps you bring your old packs up to newer Minecraft versions — right in your browser:
https://t.co/csbaKPHr5k

[Kris Cruickshank @KristopherTC]

@impulseSV Getting back into Minecraft while watching Hermitcraft 11?
I made a handy Modrinth Modpack Upgrade tool that helps you bring your old packs up to newer Minecraft versions — right in your browser:
https://t.co/csbaKPHr5k

[Kris Cruickshank @KristopherTC]

@A_MrBenMitchell @_james_gee_ @BeEV_Charging Sometimes there aren’t superchargers. Easy payments is really nice feature. Like https://t.co/rp0tJFQTx4