Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐

Entrepreneur. Coder. Hacker. Designer. Marketer. Innovator.
I only share open-source tech.

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

we're so back / it's so over (w/ Little Squeak)

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

Fight or flight?

[Nym @nym]

The UK is threatening tech bosses with prison if they don't install surveillance software on every phone in Britain.

The minister who resigned for not doing this fast enough called it "incremental change."

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

@SStricklandMMA Making a bet now that one of your drug tests comes up positive for PEDs, and not because you would take any

[NZ ☄️ @CodeByNZ]

GOOGLE JUST COMPRESSED 31GB OF AI MEMORY INTO 4GB.

That’s nearly an 8x reduction.

Memory has quietly become one of the biggest bottlenecks for running large AI models at scale. Every extra gigabyte limits how many users a system can serve and how much context it can handle.

By dramatically compressing memory requirements without meaningfully hurting performance, Google is making it possible to run larger workloads on the same hardware.

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

@marias_martin @KaiXCreator In later tweets he discusses that he reviews the code. So he lied. He misled everyone.

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

@marias_martin @KaiXCreator In later tweets he discusses that he reviews the code. So he lied. He misled everyone.

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

@marias_martin @KaiXCreator My bad, he says "forget the code even exists" inferring that he never looks at the code, and also mentions he doesn't look at the diffs. Source: https://t.co/7j5TF9mlaU

[Andrej Karpathy @karpathy]

There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

@marias_martin @KaiXCreator Literally says in the original tweet "I don't even look at the code". He lied to everyone.

[toyxyz @toyxyz3]

https://t.co/doDpfPHInc

[Rhys @RhysSullivan]

tbh i never really cared about the agents​.md vs claude​.md stuff because you can just do

ln -s agents.md claude​.md

and move on with your life

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

@NatureUnedited tastes great too
https://t.co/pCLMeDBrB2

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

this is the best one yet
@EmberSnacks

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

this is the best one yet
@EmberSnacks

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

all because you didn't create pre-push hooks in your local repo

[Branko @brankopetric00]

CI pipeline takes 45 minutes to tell you that you forgot a semicolon.

[Ahmad @TheAhmadOsman]

You don’t “run a model”
You run Kernels

The model is just a graph

The Inference Engine is scheduler / optimizer / executor

But the actual work? That happens in the Kernels

- MatMul Kernels
- Attention Kernels
- RMSNorm Kernels
- KV cache Kernels
- Quantized linear Kernels
- Sampling Kernels
- Fused “please don’t write this back to memory 9 times” Kernels

Same model, same GPU, same VRAM
Wildly different performance

Because one stack is using optimized fused Kernels that understand your hardware

And the other stack is playing hot potato with tensors through 47 tiny launches and pretending the GPU is the problem

Bad Kernels make people say:
“this model is slow”

Good Kernels make people say:
“wait how is this running locally?”

This is why Inference Engines and the Kernels implemented within them matter

The model is the recipe
The hardware is the kitchen
The Kernels are the knives, pans, burners, and the chef not cutting onions with a spoon

Most people benchmark models
The real ones benchmark the Kernels underneath

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

don't focus on building apps, build platforms instead
after that; markets
after that; standards

[@levelsio @levelsio]

I think the challenge is that everyone can now build apps

But

1) almost nobody has distribution (like an audience), or

2) the money to pay for distribution (ads or UGC), or

3) the creative genius to get distribution for free (classically called guerilla marketing)

[Chris B. Ward (e/bored) 🇬🇧🇮🇪🤐 @chrisbward]

how did the paint and plastics of the dashboard not melt or freeze and crack when up there?

[Elon Musk @elonmusk]

The car that used to be in my garage is currently in an Earth-Mars elliptical orbit and will be there for at least 10 million years

[Xor @XorDev]

Live Nightshift Effect experiment @muse