Viewing profile — cruffle_duffle
cruffle_duffle
HN member- Joined
- Mon, Nov 27, 2023, 8:02 PM UTC
- HN karma
- 845
- Public activity
- 699 items
- HN profile
- View on Hacker News ↗
About cruffle_duffle
No profile information was provided.
Recent public activity
-
comment
Comment #49215717
Well then ask the LLM to go find and pull its information from primary sources. Don’t ever rely on its own training data.
-
comment
Comment #49136765
I sometimes feel it isn’t malicious but that they don’t know the number either.
-
comment
Comment #49126467
Not only that but different countries have code regimes that make more elevators especially expensive. See how building codes in the US basically ensure there are only two real man…
-
comment
Comment #49125603
You should observe if it is the same elevator all the time and the building people just don’t understand it. Our building elevators (bank of 2) always seems to try to keep one in t…
-
comment
Comment #49125516
The problem is that in the morning the “last stop” for the elevator might be the lobby not a mid floor. And so it would have to move itself back up without any passengers or calls …
-
comment
Comment #49125299
If you like elevator hacking don’t forget the seminal DEF CON talk by Deviant Ollam and Howard Payne: https://youtu.be/oHf1vD5_b5I I watch it like once a year because it always tic…
-
comment
Comment #49088760
“ but back then the news was just one or two 30minute blocks on TV and the newspaper.” There was all kinds of quasi-serious news-adjacent crap like 60 minutes, 48 hours, etc. The b…
-
comment
Comment #49088736
That whole timespan… the absolute nonsense the “trusted media” and their “experts” were pushing with nary a single trace of critical thinking absolutely boggles the mind. How about…
-
comment
Comment #48690388
"we can start getting these answers back faster, they end up being more useful." Dude, 10x token speed is going to be absolutely nuts. Half the "parallel subagent workflow" busines…
-
comment
Comment #48689404
To be fair, versioning has always been vibes based.
-
comment
Comment #48665315
Bumping the speed of these things would be more than meaningful. It would be a massive game changer. I assert like 80% of this “multi agent parallel workflow” business is simply a …
-
comment
Comment #48665168
I mean it just depends on the price of the chip. You might just replace the chip like you would any other component. Like a video game cartridge or something.
-
comment
Comment #48665141
“ Wafer level faults probably won't matter though - neural nets are resistant to a few missing or wrong weights.” Brain science people “love” traumatic brain injury cases because i…
-
comment
Comment #48654869
To be fair Claude is plenty capable of climbing out of its sandbox. If it has shell access, it will find a way. And honestly, it’s whitelist/blacklist permission model is broken an…
-
comment
Comment #48645302
It’s really wild watching LLMs construct those calls. They batch so many different checks and stuff into a single tool call, delimit them with markers, etc. The crazy thing to me i…
-
comment
Comment #48564371
100-200 like scripts are tiny especially for something easy to scope like a vendor api. Give opus a much, much larger challenge and see what you get back. You really don’t need to …
-
comment
Comment #48554801
The docs that ship with it are a great source for the LLM who will be running the command and monitoring its output, fixing or adjusting whatever in order to complete my goal. Why …
-
comment
Comment #48371692
Paste the job description into your friendly LLM and let it attempt to find the company for you and then contact the company itself. Those recruiter spams generally just copy and p…
-
comment
Comment #48009465
I mean $40 if you are lucky or goodwill. You could get more selling it “proper” but the transaction cost of it is super not worth it (for me). When I want something out of my house…
-
comment
Comment #48009401
Remote work is absolutely brutal to a cohesive functioning society. I know people are going to slam me for saying it but is honestly true. People forgot how to interact with each o…
-
comment
Comment #47930063
I think people are looking for excuses to declare OpenAI and Anthropic teetering on the brink of failure when the actual reality is… they are wildly successful by absolutely any me…
-
comment
Comment #47885009
Pretty much. Lots of people who really were violently supportive of those measures will never admit to themselves what a horrible, entirely predictable mistake it all was. It absol…
-
comment
Comment #47863742
I feel like this is basically the answer. Things are constantly changing and it’s hard to predict what things have staying power and what is just a blip on the evolutionary railroa…
-
comment
Comment #47844181
“ I just have no faith in humanity, and do not understand why we think this is a good idea to give a browser this much access to local system resources” As opposed to dodgy windows…
-
comment
Comment #47844163
How is it any different with downloadable firmware?