Fault Localisation and Repair for DL Systems: An Empirical Study with LLMs
Jinhan Kim, Nargiz Humbatova, Gunel Jahangirova, Shin Yoo, Paolo Tonella
https://arxiv.org/abs/2506.03396
Koirilta poistettiin hampaita ilman puudutusta ja pätevyyttä helsinkiläisessä yrityksessä, epäilee poliisi #eläinoikeudet
Let's say you find a really cool forum online that has lots of good advice on it. It's even got a very active community that's happy to answer questions very quickly, and the community seems to have a wealth of knowledge about all sorts of subjects.
You end up visiting this community often, and trusting the advice you get to answer all sorts of everyday questions you might have, which before you might have found answers to using a web search (of course web search is now full of SEI spam and other crap so it's become nearly useless).
Then one day, you ask an innocuous question about medicine, and from this community you get the full homeopathy treatment as your answer. Like, somewhat believable on the face of it, includes lots of citations to reasonable-seeming articles, except that if you know even a tiny bit about chemistry and biology (which thankfully you do), you know that the homoeopathy answers are completely bogus and horribly dangerous (since they offer non-treatments for real diseases). Your opinion of this entire forum suddenly changes. "Oh my God, if they've been homeopathy believers all this time, what other myths have they fed me as facts?"
You stop using the forum for anything, and go back to slogging through SEI crap to answer your everyday questions, because one you realize that this forum is a community that's fundamentally untrustworthy, you realize that the value of getting advice from it on any subject is negative: you knew enough to spot the dangerous homeopathy answer, but you know there might be other such myths that you don't know enough to avoid, and any community willing to go all-in on one myth has shown itself to be capable of going all in on any number of other myths.
...
This has been a parable about large language models.
#AI #LLM
HoneySat: A Network-based Satellite Honeypot Framework
Efr\'en L\'opez-Morales (Texas A&M University-Corpus Christi), Ulysse Planta (CISPA Helmholtz Center for Information Security), Gabriele Marra (CISPA Helmholtz Center for Information Security), Carlos Gonz\'alez (German Aerospace Center), Jacob Hopkins (Texas A&M University-Corpus Christi), Majid Garoosi (CISPA Helmholtz Center for Information Security), El\'ias Obreque (Universidad de Chile), Carlos Rubio-M…
@… Hey bzgl. #HomePod im Kontrollzentrum in deinem iPhone/iPad kannst Du den Homepod auswählen und lauter leiser machen.
"Seven years and six months!" Humpty Dumpty repeated thoughtfully.
"An uncomfortable sort of age. Now if you'd asked MY advice, I'd have
said 'Leave off at seven' -- but it's too late now."
"I never ask advice about growing," Alice said indignantly.
"Too proud?" the other enquired.
Alice felt even more indignant at this suggestion. "I mean,"
she said, "that one can't help grow…
Decoding TCP SYN for Stronger Network Security
https://www.netscout.com/blog/asert/decoding-tcp-syn-stronger-network-security
A brief look at TCP SYNs observed by low impact honeypots. I mainly sought evidence for source address spoofing and a…
I have a HomePod. I talk to it to control my home. I occasionally ask the weather. And yet I still feel more magic when I hit a button in an app to set a lighting scene. Especially as I have the thought, and then click a button and it just does it.