HN user

MaxikCZ

1,460 karma
Posts2
Comments641
View on HN

What? Free ride after I bought something is not allowed? I have to be productive first to buy it, the purchased item is the result of my work, not something I have aquired a right to be productive about later.

+ theres still a lot of maintenance and other expenses going on making it definetly not free ride, I dont understand your position at all.

A lot of words explaining how something is hard to do because physics but in my layman experience any speaker I heard that didnt cost $500+ sounded horrible regardless of size, while my M1 Macbook Air sounds better than all of those, while keeping tiny formfactor.

Clearly it can be done, its just noone seem to be investing in RnD enough.

NixOS 26.05 23 days ago

15 hours later and noone taking that ragebait, seems healthier than most communities to me as a total outsider.

Same question, same answer: In pixels/second? Sure!

What are you trying to accomplish by those questions? Are you genuinely asking, or just baiting? If the former, didnt answers to your previous question make it clear that your question makes less sense than you might assume?

Claude Opus 4.8 2 months ago

I wish I knew how to make it regressively verify its assumptions, like a kind of hook but firing before a sentence is written, or perhaps after and then corrected. I feel like it assuming things clearly wrong is its biggest weakness.

drop the human pretense entirely. Make the agent sound clinical, robotic

Id pay to be able to reliably set LLMs to this mode, but ofc because LLMs are taught on corpus of HUMAN text, they always, sooner or later, return to the good old penpal mode.

Also, in Claude Desktop app, I ask to edit a file, it complains it cant access files, I then realize im in Chat and not Code interface. Why cant such a smart machine figure out to switch the modes, or borrow the skills/abilities from one tab away into this tab? Instead I get A4 page of text explaninig what can I do to edit the file myself or how to feed it, but the "just click Code" is just never there. I would guess this is just a system prompt away, why is all this still so neglected?

This is the pain point that existed for years now and its still not solved at all.

"If A, do X. Do B,C,D. Do A" - and it just never uses X because "it forgot".

You just cant trust that the time you spend building rules will actually pay off, in fact you can trust that it will fail you sooner or later.

RAG, Harness, Skills... all was supposed to fix this, but in reality it never had.

Claude Opus 4.7 3 months ago

Lul, Im embracing this "cringe" you talk about :) Everytime I read it it makes me laugh :D

Reverse proxy itself will do barely any defense, what you need in combination is an authgate (authentik, authelia), and here we are moving from "simple reverse proxy" to fun weekend activity and then some getting it to work as expected. + it kills the app auth flow, so only web interface is suitable for this.

Yea its pretty bad, there are pages of non-fixed confirmed exploits, you really shouldnt let it face the net.

VPN is one solution, and actually the only real solution for app-based jellyfin (TV, phone apps) I found so far.

Another is to host Jellyfin behind reverse proxy, and have a completely independent authgatein front of it (authentik, authelia). Jellyfin even supports LDAP (trough plugin), so you dont have to login twice per visit. The downside is only web interface can be hidden this way, as apps will break expecting jellyfin auth page and finding something else.

[dead] 4 months ago

more than clickbait I hate why its on a frontpage at all. Like, who even is upvoting such trash?

I heard that we often get cold/flu/sore throat when we get too cold outside, because the inside of our orifices is kept at a certain temperature to kill those bacteria/viruses. When we get too cold, we are unable to kill them fast enough, and get overrun. Staying in 70-100°C air for prolonged time must also heatshock those parts of our bodies, so I guess we kinda sterilize it that way.

At least my 2c why I think its helping

Actually its just one opus aimed at a codebase with one goal, and instruction to spawn 2 subagents: one worker, that comes up with implementation plan, one validator that validates the proposed plan against my guardrails, and then return back to subagent1 to implement this, where the second subagent again tests the implementation.

One loop of this can take 20-60 min, and eat 2-5% of my week limit. I have to actively slow myself down to not burn trough more than 15-20% of my weekly limit in a day (as I also like to work on it on weekends)

Sadly I cant share the actual problem I am working on as its not my secret to disclose, but its nothing "crazy", and I am so surprised others dont have similar experience.