Viewing profile — swordsith
swordsith
HN member- Joined
- Fri, Jan 16, 2026, 6:01 AM UTC
- HN karma
- 42
- Public activity
- 74 items
- HN profile
- View on Hacker News ↗
About swordsith
No profile information was provided.
Recent public activity
-
comment
Comment #49201363
The source of the bloat is less vibecoding and more architecture missteps and reliance on using web interfaces for everything.
-
comment
Comment #49172136
Sometimes after a larger source draft with AI before I even touch the program I start to pick up on some of the holes in my prompts caused bugs/unintentional mechanics to be potent…
-
comment
Comment #49121971
Saying we're at the Peak of LLMS is like saying we never went further than everest, these are probabilistic state machines sure, but the real value is the effort put into tooling a…
-
comment
Comment #49105865
Could send random characters along with 'keep going' and it would change nothing, the seed is whats causing deviation between these responses.
-
comment
Comment #49073216
Auto is not a model, auto is the mystery box option that cursor gives people who are too slow to read a documentation and flip a few switches. With auto you're going to get routed …
-
comment
Comment #48982987
I'd bet your issues with blender could be fixed with configuration or rebuilding the program with older graphics renderers available, it being open source makes alot of the prefere…
-
comment
Comment #48875040
put my same phone number on 10+ google accounts, if you're skipping this you look like a bot, how should google be able to tell you apart from all of the bots.
-
comment
Comment #48700168
Myocarditis and blood clots aren't a side-effect, they are life altering and ending.
-
comment
Comment #48624122
why I reject thing that makes other peoples lives easier even if it makes peoples lives easier.
-
comment
Comment #48566104
I can only stand to use the cursor CLI at this point, but it's usable I like to be able to switch models when one gets stupid or guard-railed, on the pro plan you get so much usage…
-
comment
Comment #48520392
They tried but only with a subagent that was not entertained with their attempts. Newer LLMs usually come out of the box with pre-prompts to avoid prompt injection so they don't ge…
-
comment
Comment #48428740
programmers will get the dark-light mode preference from my browser, and still choose to blind me.
-
comment
Comment #48403293
I loved this book, especially the release of tension at the end.
- comment
-
comment
Comment #48327013
from BAM faq post the other day[0]. FAQ Q: If you want a resolution, why not just pay the money demanded online? A: We are completely willing to sit down and figure out a fair, rea…
-
comment
Comment #48305744
DON'T LET THE LIGHT DIE OUT! (bring it back up plz)
-
comment
Comment #48283025
Personally I feel a vulnerability in local code (unshared ai slop) is much less likely to be exploited, than for say a npm package update that will pwn you as soon as it loads up.
-
comment
Comment #48268256
How long will it be until you can't spin the thread and fabricate your clothes stitch by stitch because you're out of practice?
-
comment
Comment #48268173
Nice reusable libraries are still a core part of most AI projects, but honestly I think it's not a terrible approach with all the updating dependency malware issues with stuff like…
-
comment
Comment #48037943
Facing reality is difficult for these euro types, they feel an need to to simultaneously hate America while also wanting to be like it.
-
comment
Comment #47972488
Claude is notorious in my experience to lie directly to your face (even if its baffling) instead of using the web tool. I'll never prompt it without saying 'use web tool' Its ridic…
-
comment
Comment #47957284
idc its obviously Ai, your algo is wrong.
-
comment
Comment #47957280
Seems like a de-webbed fork of this is a no brainer. its crazy what they think people will just take lying down from a open source project.
-
comment
Comment #47930909
Hopefully this means opeani wont exclusively distribute codex app through microsofts drm system
-
comment
Comment #47839139
Very obviously AI written, could tell by the end of the first sentence. Could've been a interesting read.. if you wrote it.