ai_slop_hater

Next step is go down one more level to ditch SQL and learn LMDB and/or RocksDB.

What you are referring to as "no different than what most have done" is training on public data. What Cursor did is

1) Fork VSCode and pretend that they made some kind of "AI IDE"

2) Fork a Chinese model and pretend that they trained their own model

Company with zero moat and terrible products that keeps lying to everybody

Same idea, take somebody else's work and present as your own.

Don't lie. You forked a Chinese model.

That company has always been garbage.

Elon Musk would love it lol

What is Mythos like? Asking as someone who never had access to it.

Isn't this more expensive than always using the same model, since, as I understand, by routing to different models you give up on cache?

I ran out of usage using GPT-5.5 and had to buy a second subscription. I now switched to GPT-5.4 which is basically 2x usage.

I've grown to hate executives. This is obviously an AI-generated nothing burger. They never mean what they say publicly.

They all have one thing in common, the fact they suck. You don't need an "AI framework"

People don't go to universities for courses

Why is comment from padolsey dead? Seriously, something fishy is going on on this website.

Managing AI context.

I meant software engineers, not most of all living people

Why can't you test AI chats?

don't forget to fork and rename a chinese llm

most people are behind the curve

What do you mean spacex has? Did spacex stock go down?

It's a good thing. I hate MCPs from the bottom of my heart because they always stay there and bloat the context window. Also, usually developers who develop them don't know what they're doing, so the MCP responses also bloat your context even further.

If only they could add an option to disable features you don't use

Pretty much the same point I made https://news.ycombinator.com/item?id=48500537

Every day I am more and more convinced that AI labs can't code.

If i have a really hard problem or big refactor, i use workflows.

What is a "workflow"? Is this some kind of new feature?

For how long can you use Claude Fable on most expensive Anthropic subscription? I already went from using gpt-5.5 xhigh fast to using gpt-5.4 xhigh after OpenAI halfed usage recently.

In fact, one study I cite in the book found that something like 80% of founders of venture-backed companies will no longer be CEO even three years after an IPO.

Why? Is there something that inherently prevents founders to remain in control after IPO?

They don't know what a megabyte is

And the great era of rewriting in Rust has begun (again).

I saw a comment on HN a while ago. I don't remember exactly how it was worded, but roughly it was something like: if you are self-taught (which I am), you will have to do many shitty jobs before you get a good one. That is how I think of my situation. I am still doing shitty jobs, but I think that the shittiest ones are already behind, and if I had not taken them, I would not be where I am now.

you need to bring others up around you as well

I am not 100% sure what you mean here, but I don't think that I have the authority or reputation to "bring up others." I find that telling other people what to do is futile, and the best I can do is leave them alone and let them learn from their experiences, or else you might be labelled a "rock star," which is coincidentally being discussed on lobste.rs right now:

https://lobste.rs/s/uvwcdo/cleaning_up_after_ai_rockstar_dev...

Because nobody is hiring so if I got an offer I had to accept it.