Viewing profile — HappySweeney
HappySweeney
HN member- Joined
- Thu, Sep 20, 2018, 2:31 PM UTC
- HN karma
- 590
- Public activity
- 365 items
- HN profile
- View on Hacker News ↗
About HappySweeney
Recent public activity
-
comment
Comment #49214112
Only if you average it all out. The over 65 crowd does not produce more than they consume.
-
comment
Comment #49116676
Canary tests on my data showed I needed xhigh to get good results, but they are good.
-
comment
Comment #49035571
Your experience is night-and-day from mine. Both myself and the AI correct and remove each other's gaps in understanding. There is never what I would call arguing. Disagreements ar…
-
comment
Comment #48947253
The hacky string matching is what I started with, but there was always new ghost text. I turned suggested prompts off which helped, but idle hooks plus ensuring the terminal doesn'…
-
comment
Comment #48937943
I have a more primitive setup where I use Gemini, Claude, and Codex at the same time and cultivate expert contexts. Each of them lives in their own tmux session so they can read ea…
-
comment
Comment #48817516
this site has some popup that hijacks the page and tries to trick you into installing an antivirus with fake infection reports. Closing that popup sends you to walmart.com
-
comment
Comment #48784466
In my experience, audit findings decrease in frequency as a codebase matures. Was Fable doing greenfield work?
-
comment
Comment #48706036
They measured density, not the probability of getting one.
-
comment
Comment #48628582
A bunch of links open a hardcoded browser (like help links within Visual Studio). Executives have OKRs to meet.
-
comment
Comment #48584693
I find that when an LLM jumps into tasks it was not told to do (or even worse, doing things it was explicitly told not to), it is a good sign the context is too full, and you shoul…
-
comment
Comment #48543610
I have an optane and lots of ram, so I tried full-fat models for writing some function overnight, as I get about 0.7 t/s. My current go-to test is to update a scalar function to tr…
-
comment
Comment #48439510
I think its common to develop an adversarial-collaborative approach to getting some semblance of quality out of AI. I personally favour using multiple models for different roles, h…
-
comment
Comment #48236445
Code review is the main thing I use LLMs for. I have found it to be remarkably candid when you tell it the code came from another LLM (even name it). I was running Kimi K2.6 Q4 loc…
-
comment
Comment #48120369
They are redeveloping much of that electron-based code back to Win32 as part of their quality improvement initiative.
-
comment
Comment #47547346
Haven't there already been a few cases, each of which found that mechanically-produced works are not copywritable?
-
comment
Comment #47504502
If I had to guess it would be "campaign contributions".
-
comment
Comment #47402431
Are buckyballs organic?
-
comment
Comment #47173946
[flagged]
-
comment
Comment #47013857
Agreed. I believe it's well within Google's ability to auto-edit the sponsored segments out within an acceptable error margin.
-
comment
Comment #46892998
fwiw Penn Gillette no longer calls himself a libertarian.
-
comment
Comment #46434213
If you don't exclude your build folders from the scan it will slow everything down tremendously.
-
comment
Comment #45993319
Don't legitimate IQ tests top out at 160 for adults?
-
comment
Comment #45823941
Do investors ever say "ok, time to panic"? Aren't they always just going to shill their bags? Why should we listen to them?
-
comment
Comment #45503453
It's in the article. I'm happy to read the bill and watch your linked video once my workday is over.
-
comment
Comment #45503238
> In the sense that you can sue to have the order challenged? That's a good question. The article doesn't say and I haven't read the bill. > Were the bank accounts seized before or…