bionhoward

It’s amazing how much Python punishes you for modularizing your code

I’m heavy into rust and never really use golang, but one big benefit of go over rust is compile times are significantly quicker, which could be more fun if you’re running CI checks 50 billion times

Yeah it’s a coding beast if you get it dialed in right

gotta admit i groaned a bit at this because it would make rust more complicated, but on my 2nd read i realized:

- some things (compile time bounds checking tensor shapes) are hard / impossible to implement now; "pattern types" could be great for that

- however "no panic" is already handled by clippy, might not be much uplift for doing that at a type level.

my 2c: it's great to be excited and brainstorm, some of these ideas might be gold. conveying the benefit is key. it would be good to focus on stuff for which rust doesn't already have a workable solution. i like the pattern types, the rest would take convincing

Anthropic is not trustworthy for this because they force every Claude Code user to agree to a noncompete while also opting them in to model training.

That means, by default, every Claude Code user is actively getting royally screwed

surprisingly accurate! Is Gary the AI equivalent of the “nothing ever happens” guy?

genius, great idea and follow through, please keep it up, this could improve the ML industry tremendously, maybe some einops inspired interface for this would be good?

building this openclaw thing that competes with openai using codex is against the openai terms of service, which say you can't use it to make stuff that competes with them. but they compete with everyone. by giving zero fucks (or just not reading the fine print), bro was rewarded by the dumb rule people for breaking the dumb rules. this happens over and over. there is a lesson here

signal should just add better API / bot stuff and then we could all use that. there's no way OpenAI would be trustworthy for this; slack certainly isn't

found a bug searching for "collagen":

  Failed to execute 'removeChild' on 'Node': The node to be removed is not a child of this node.
  Something broke. We're working on it, but in the meantime, try reloading the page. If that doesn't work, come back later.

  Error ID: b846e2e2ba3b483ab93f10e72ef76820

  NotFoundError: Failed to execute 'removeChild' on 'Node': The node to be removed is not a child of this node.
    at ds (https://pillser.com/assets/entry.client-DWgmqxdv.js:1:112074)
    at gs (https://pillser.com/assets/entry.client-DWgmqxdv.js:1:113602)
    at ys (https://pillser.com/assets/entry.client-DWgmqxdv.js:1:113850)
    at gs (https://pillser.com/assets/entry.client-DWgmqxdv.js:1:113728)

Yes! The paywalled SQL documents are a big annoyance

Yup, I’ve been crowing about these customer noncompetes for years now and it’s clear Anthropic has one of the worst ones. The real kicker is, since Claude Code can do anything, you’re technically not allowed to use it for anything, and everyone just depends on Anthropic not being evil

Why act like it’s a mystery when the Claude Code repo clearly explains:

When you use Claude Code, we collect feedback, which includes usage data (such as code acceptance or rejections), associated conversation data, and user feedback submitted via the /bug command.

They subsidize Claude Code because it gives them your codebase and chat history

Would SRAM make weight updates prohibitive vs DRAM?

Gemini is absolutely not Gryffindor since it auto-opts users into training AI on their codebases without informed consent

Anthropic also has legal terms that say no one is allowed to use the service for anything work related, but nobody seems to care

Cursor still wins over Claude Code because Cursor has privacy mode

I think it’s more about deciding how much to think about stuff and not a model router per se. 5 and 5.1 get progressively better calibrated reasoning token budgets. Also o3 and “reasoning with tools” for a massive consumer audience was a major advance and fairly recent

model provider CLIs are a trap, less freedom of choice, less privacy, way more prohibitions buried in the fine print

Good reason to use Cursor, you can insta-switch to whatever model you want and even run diverse models from different providers at the same time. If one of em isn’t working then you can try something else instead of being stuck on one model provider

And here I thought it was a pedantic word for “data box”

Is using these terminal agents with customer noncompete and no privacy questionable when cursor has the same models and privacy mode?

The point is it’s sucking your data into some amorphous big brother dataset without explicitly asking you if you want that to happen first. Opt out AI features are generally rude, trashy, low-class, money grubbing data grabs

Rust for everything, I could explain but it would get rude

Rust feels easy for me, could it be we’re just used to what we use more?

Anyway, it’s all pretty easy, what’s the use arguing which of multiple easy things is easiest?

Wouldn’t a breakpoint or log message require the code to compile and run in order to work?

Doesn’t compare, because Cursor has a privacy mode. Why would anyone want to pay OpenAI or Anthropic to train their bots on your business codebase? You know where that leads? Unemployment!

Meh, what’s the point if it’s got no privacy, which companies want to let OpenAI read your codebase? Cursor keeps winning because of privacy mode IMHO, there is no level of capability which outweighs privacy mode

That time to first token is impressive, it seems like it responds immediately

Is this a “bullshit injection?”