241 karma · joined September 12, 2024
If the goal is just to output code that does not show any linter errors, then yes, choose a dynamically typed language.
But for code that works at runtime? Types are a huge helper for humans and LLMs alike.
Guatemala is the only place outside the US where I was not quoted 3-5x Uber prices by very pushy taxi drivers.
Taxi drivers are scam artists and thieves. There’s no reputational damage either, as you will never see them again.
Uber solves the reputation problem: every driver is rated, and poorly rated and badly behaved drivers do not get to work for them.
> - Cursor (can't remember which model, the default)
> - Google's Jules
> - OpenAI Codex with o4
Cursor's "default model" rarely works for me. You have to choose one of the models yourself. Sonnet 4, Gemini 2.5 Pro, and for tricky problems, o3.
There is no public release of o4; you used o4-mini, a model with poorer performance than any of the frontier models (Sonnet 4, Gemini Pro 2.5, o3).
Jules and Codex, if they're like Claude Code, do not work well with "Build me a Facebook clone"-type instructions. You have to break everything down and make your own tech stack decisions, even if you use these tools to do so. Yes they are not perfect and make regressions or forget to run linters or check their work with the compiler, but they do work extremely well if you learn to use them, just like any other tool. They are not yet magic that works without you having to put in any effort to learn them.
For someone looking to build a large embedding search, fast static embeddings seem like a good deal, but almost too good to be true. What quality tradeoff are you seeing with these models versus embedding models with attention mechanisms?
It took multiple tries to get the model to convert at all to the mlpackage format, and then a lot of experimenting to get it to run on the ANE instead of the GPU, only to discover that constant reshaping was killing any performance benefit (either you have a fixed multiplication size or don't bother), and even at a fixed size and using the attention mask, its operations were slower than saturating the GPU with large batches.
I discovered an issue where using the newer iOS 18 standard would cause the model conversion to break, and put an issue in on their GitHub, including an example repository for easy replication. I got a response quickly, but almost a year later, the bug is still unfixed.
Even when George Hotz attempted to hack it to use it without Apple's really bad and unmaintained CoreML library, he gave up because it was impossible without breaking some pretty core OS features (certificate signing IIRC).
The ANE/CoreML is just not serious at all about making their hardware usable at all. Even Apple's internal MLX team can't crack that nut.
https://chatgpt.com/share/68104c37-b578-8003-8c4e-b0a4688206...
Thank you. Seriously.
Note: I searched "Protein bars", and it treated all protein bars equally. The 1st-20th cheapest had <15g of protein per bar. I had to scroll down to the 50th-60th to find protein bars with 20g of protein, which surprised me for being cheaper than Kirkland Signature's protein bars.
I've used Cursor for shipping better frontend slop, and it's great. I skip a lot of trial and error, but not all of it.
Take the time to read it.
I'm sure it works great, but at that price point, I'm stuck with self-hosting Postgres+pgvector.
1,000,000,000,000 tons of CO2 / (28.5 tons of CO2 per wooden house) = 35 billion wooden houses.
If you just want to achieve carbon neutrality, we're outputting 40 billion tons of CO2 per year.
(40,000,000,000 tons of CO2 per year) / (28.5 tons of CO2 per wooden house) = 1.4 billion wooden houses, per year
That's not feasible for many reasons.
We need and use cement and aggregate anyway, and it's a large emitter of carbon. It's good that someone discovered a way to use it to sequester CO2 to reduce or offset its carbon emissions.
This is a real killer feature that will dramatically slow adoption of non-Chromium browsers, even with Google defanging ad blockers.