the boys gc right now

mcp > cli im glad this debase is not as active anymore. i use both every day. they just serve different purposes cli for stuff the model already knows. git, gh, npm, docker, file ops. trained on man pages, and costs almost nothing in context. if im already signed in locally theres no reason to wrap it in anything mcp for most integrations. slack, notion, linear, twitter and its neat to have a protocol for all these integrations - add one server to my teams cursor and everyone gets access - auth once, persists, same locally and in cloud it also just feels better in cursor. rich icons, traceable, you can easily follow whats happening (tbh not reading that much) cli for personal, mcp for team (with oauth)

Anthropic: Claude identified and trapped the souls of 8 djinns in its new model. We believe that they are mostly benign OpenAI: we have cloned the neural structure of the cockroach. This will make our model 8000x better at using Salesforce Mistral: we exist

One day AI will cure a disease. And many people in this platform will look you dead in the eye and say “the cure was already in the corpus of human knowledge and it’s not truly intelligent”

The high agency triangle

I keep seeing this complaint and I don't get it unless you don't regularly use macOS. The entire app is contained. There's no installer (uninstalling should be either with cache files but whatever) But so many times when I just give users the .app they open it in their downloads folder. This is an easy way to install to the applications folder and tell the user "you are putting this here. This drag is authenticating it." Rather than a multi step wizard that might be sneaking and installing things it shouldn't

I gave it a go, and it's actually pretty cool. I wasn't really using ChatGPT much before, but I subscribed. Some non-coding use cases I tried: - It copied over about a hundred pages of work/study notes from Notion to Obsidian locally and formatted them nicely in Markdown. - It also organised my rather messy Obsidian vault. - It rewrote and reorganised my company's technical onboarding material (I'm responsible for that). It created images and infographics for the material, then emailed them to my company address so I could upload them from my work laptop. I did all of this in about 30 minutes. I'm still figuring the tool out, but it's genuinely useful. If you already have a ChatGPT subscription, its worth the try.

There's a folk belief that LLMs & agents are incapable of doing math, because they can't count the "i's" in "raspberry" or something. That claim has been obsolete for at least a year now and if you're making it, be aware it's a shibboleth for "I'm not paying attention".

Putting a browser inside a superapp seems obvious in hindsight, somehow.

so you're telling me every week is release week now?

OpenAI is becoming a high taste product company They used to be much more cringe, but something’s changing internally

can't decide which of the next 7 announcements i'm most excited about

The MacBook went from a joke to the most serious laptop on the market.

inference is very profitable and probably a good opportunity to understand some basic business math 1. companies buy long lived assets like GPUs. these are one time costs and the asset depreciates over time 2. once you own this asset, you can plug it in and produce tokens which you can sell. the cost of goods sold here can be very low and you might be making 90% margins at scale, this is why we say inference is profitable 3. then you also hire employees to do r&d work to improve your systems, come up with new models, expand the business if you add these 3 up you end up with $0. you're not producing a profit because the business is growing and you're reinvesting it all buying assets or r&d to meet demand if it's obvious to other people the business is working, you can raise money from them to accelerate all these numbers so they max out in 5 years instead of 25 so on paper you'll be "losing money" every year but that's because you want to make sure you lock down the opportunity before someone else the bigger your market is the bigger this burn can be because it's a function of potential so when you see these companies losing a lot of money it doesn't mean the whole concept of their business broken it's possible they misjudge and overinvest on 1 3 and will suffer some consequences but fundamentally 2 does work

OpenAI is so washed they are going to release a Mythos level model at half the price

this is actually crazy. there's a new, improved, composer model every 5 hours. that is ~5 improvements per day

"Unless there's a specific app or game you want to run.. [just get a $599 MacBook Neo]"

The MacBook Neo is such an interesting machine that it coaxed a thousand-word-essay out of me

Just edited a 4k short-form video in premiere on the MacBook Neo....why is it performing so well???