I think the issue of web sites blocking AI is going to lead to, well..... not sure, but probably nothing good. The issue above was the API claude was trying to write against could not be verified because the website was blocking all AI useragents.Smucky wrote: Fri Apr 24, 2026 7:15 pm I think I spent like two hours today trying to get a script to auto update the minecraft mods on my daughter's laptop. I have short list of mods I grab:
....
I'm getting mad at this point and it can tell. It responds
It continues to tell me that I am not running the right version of the code it made for me:Fair criticism — I should have actually queried the API to verify my assumption about what ImmediatelyFast's game_versions arrays look like, rather than guessing. Let me do that now.Which was the same issue as sonnetMy saved file has the new logic. Given your output is byte-for-byte identical to the first run (same mod filenames, no (matched on …) notes anywhere, same skip), the most likely explanation is that the file you're executing as ./update_mods.py isn't the one I gave you — maybe the download didn't land where you thought, or the shell is resolving ./update_mods.py to a different copy than you edited.![]()
And then today, I'm debating on moving my main software stacks in the future to all golang. There's a good golang group on reddit, but I'm not going to that place, so lets make AI go there and dig up the best "web stack" libraries for us to use
But reddit and all the reddit mirrors have blocked AI access:
There are no post titles, scores, or search result snippets to extract from this content. If you'd like me to analyze different web content, please share that instead.
● Fetch(url: "https://teddit.net/r/golang/search?q=sa ... top&t=year", prompt: "List post titles, scores, and brief snippets from search results.")
⎿ Error: Claude Code is unable to fetch from teddit.net
● Tried it (and the rest of the active redlib mirrors). Verdict: no — they don't help from this tool.
What I hit:
- redlib.catsarch.com, redlib.r4fo.com, redlib.cow.rip, redlib.perennialte.ch → all 403
- redlib.privadency.com, eddrit.com → blocked by Anubis (proof-of-work bot challenge)
- redlib.nadeko.net → 502
- red.artemislena.eu, redlib.privacyredirect.com, l.opnxng.com → connection refused / closed
- safereddit.com → redirects to catsarch (which 403s)
- old.reddit.com, teddit.net → blocked at the WebFetch layer itself
- safereddit.com → redirects back into catsarch
The pattern: WebFetch's user-agent fingerprint trips bot detection across every Reddit mirror. Anubis specifically is designed to block exactly this kind of headless fetch with a JS-required PoW challenge. Even if a mirror is
technically up, it's gated.
What actually works for getting r/golang content into our conversation:
1. Google site: searches — the path I used in the first answer. Coverage is patchy because Google has deindexed a lot of Reddit lately, but it surfaces aggregator articles that quote/summarize the threads.
2. You paste the thread — if you find a specific r/golang post you want me to dig into, paste the URL and I'll have you copy the content in, or paste the relevant comments directly.
3. Reddit's JSON API with auth — would work, but needs OAuth credentials I don't have set up here.
I guess the thing I find ironic is the current version of LLMs got their knowledge from downloading everything from the internet. But now they are getting more and more blocked from accessing internet resources.