1 is definitely false right now. I gave specs, tests, full datasets, reference code to translate to an llm and still produce garbage code/fall flat on it's face. I just spent one week translating a codebase from go to cpp and i had to throw the whole thing out because it put in some horrible bugs that it could not fix even burning 500$ worth of tokens and me babysitting it. As i said it had everything at it's disposal: tests, reference impl, lots of data to work with. I finally got my lazy ass to inplement it and lo and behold i did it in 2 days with no bugs (that i know of) and the code quality is miles better than that undigested vomit. The codebase was a protocol library for decoding network traffic that used a lot of bit twiddling, flow control, huffman table compression, mildly complicated stuff. So no - if you want working non-trivial code that you can rely on then definitely don't use a llm to do it. Use it for autocomplete, small bits of code but never let the damn thing do the thinking for you.
Oh, I agree. Anthropic themselves proved that even with a full spec and thousands of human-crafted tests, unsupervised agents couldn't produce even something as relatively simple as a workable C compiler, even when the model was trained on the spec, tests, the theory, a reference implementation, and even when given a reference implementation as an oracle.
But my point was that I don't think the development of Claude Code itself isn't supervised, hence it's not really "vibe coded".
I recently moved from a docker-compose setup with portainer as a manager to podman+quadlets+cockpit . After the initial pain of migration i'm really happy! I can also manage VMs, volumes, and check systemd logs so it's a good all-in-one solution for managing standalone servers. Also i think it uses systemd activation so it's really light on resources. For someone who dislikes the proxmox approach of custom kernel/os this is a good alternative.
ZKPs are mentioned in the technical specs but no implementation yet. Would go for lack of standardisation / lack of harware support for these protocols as the explanation but who knows..
Block access to your servers and offer firmware for their watches with access to your servers. Most people who use these watches are nerdy enough to dislike this behavior and able to flash a new firmware.
I remember this was initially developed at king games (candycrush saga authors) before they got acquired. Probably that's the reason for the weird licensing model
That's actually funny.. considering that the main reason TikTok ban was proposed was the lack of censorship of sensitive topics like a certain genocide
- Make the preview text length configurable, I'd like to read more of the original post before I dive into comments
- The search is rather annoying. I found the post on hn web then it took me a while to find it in the app to comment on it. Maybe implement a filter on the main page for precached stories?
- A bit of styling / spacing / coloring would be nice. For example the stories feel like they blend into each other. The app is monochrome by design but I think a bit of color could guide the eye on content heavy views
reply