xendo

This is literally next token prediction model, can be useful in place of random weight models since it actually gives verifiable output.

This applies to code btw, it's so much nicer to read a human made pull requests. It's also much faster as people tend to be lazy and produce denser code.

One of my page was 2nd on the main page trending towards 1st, a single flagging pushed it to the middle of the second page.

It's clearly heavily down voted, just look at when it was added, how many points it has and its relative position.

Every ducking time I hear Anthropic or OpenAI did some great engineering it either turns out to be shit (c compiler) or stolen (this). Bravo! LLMs are such a marvelous technology, but being developed by such dushbags that I suddenly root for Meta. Disgusting.

My expectation is that those AI primary forks will degenerate quickly. Maintaining OS requires a lot of judgement, direction, agents tend to turn softeare into big pile of disconnected features.

This one is quite difficult, it sacrifices some readability for cleverness and conciseness. I find Algorithmic Thinking by Zingaro much more approachable but almost as dense.

There are certain parts of my job that can be mediocre and I'm happy to offload them to models. Those are, however, not the parts that count.

I will take my chances. Software is part of my identity and I won't abandon it that quickly.

I don't agree. I'm recently a huge believer in Programming as Theory Building. The software creation itself is the part that makes you understand what you are building. It's impossible to understand things before you start building them, initial prompt can help you explore, but the idea that after that you can lean back is ridiculous. Most or maybe even all successful software projects are still heavily relying on the best software engineers. That's why anthropic and others are still hiring SDEs.

Both her as well as huggingface this should be investigated by law enforcement and people responsible should be punished.

Just look at the keyboard and sort all characters by how probable you think they are next, type one and start from the beginning.

Have you read the page? I'm the COE of HTMX. I'm the boss.

100%. Making it a whole day makes it easier to sell and stick to, that's it. It's just brutal to have a whole day when you need to focus and not just mindlessly prompt.

I made the site to convince my boss to let me not use AI on Fridays. Hoping to get some noise around it to make him believe it's real.

For anyone that does LLM supported work it's crystal clear that skill decline is real. Surprisingly, the leadership at my work doesn't give rats ass about it. They published AI engineering manifesto, pushing for loops, workflows, advocating for producing many times more code. All of this ignoring the elephant in the room.

@antirez is a very prominent open source contributor that gets lot of shit done with LLMs. Mitchel Hashimoto is also open about using LLMs to speed up his work. There are some caveats attached: neither of them is doing crazy loops or graphs producing thousands of lines of code, they are both amazing software engineers and they know what they are doing.