Posts by axleyjc@federate.social
 (DIR) Post #ASoDh7n7F2ikeHjrrk by axleyjc@federate.social
       2023-02-18T16:08:25Z
       
       0 likes, 0 repeats
       
       @simon Do they lock their documentation behind a support paywall? That's not only annoying friction - even if you have a support contract - but also a self-own.
       
 (DIR) Post #AYetjHxENOmT5WVJXE by axleyjc@federate.social
       2023-08-12T15:24:38Z
       
       0 likes, 0 repeats
       
       @simon Curious: how do you know the llm answers are trustworthy vs. sounding like they are trustworthy? How do you avoid this result: https://arxiv.org/abs/2308.02312?
       
 (DIR) Post #AaIZA1V3Lj3Sh8FvWq by axleyjc@federate.social
       2023-09-30T16:33:23Z
       
       0 likes, 0 repeats
       
       @simon @briankrebs use of the word "potential" in response to Brian's mention of harms to subsets of people comes off as dismissive of real harms happening now. May not have been your intent. Or you pivoted from harms to people to "disruption" in the abstract which is most often used to refer to jobs and industry impacts vs. individuals.
       
 (DIR) Post #AaIefSkwYp0zybV1n6 by axleyjc@federate.social
       2023-09-30T16:45:05Z
       
       0 likes, 0 repeats
       
       @interpipes @ncweaver @simon @briankrebs there's lots of code that compiles but is completely insecure! And the fact that many LLMs used for coding aren't trained on good code means there's a lot of latent bad code lossily compressed in the data set. If you use one, use one that curates the training data.This is a great balanced review of using an LLM for development: https://youtu.be/_nG6d6HSGB4
       
 (DIR) Post #AaIefUpGrhfIObXVoW by axleyjc@federate.social
       2023-09-30T17:30:07Z
       
       0 likes, 0 repeats
       
       @interpipes @ncweaver @simon @briankrebs The most popular refrain on stack overflow when developers asked questions about problems with cross origin web requests was to respond with a recommendation to add the header Access-Control-Allow-Origin: *Replies from the original posters thank them for that "solution". Of course it "worked", but only if you narrowly define "worked" as "functions" vs "functions securely"Fallacy of LLMs as sources of truth is that frequency correlates with truth.
       
 (DIR) Post #AaKgn90OSwvxGHR7lA by axleyjc@federate.social
       2023-10-01T17:10:02Z
       
       0 likes, 0 repeats
       
       @simon @jernej__s @interpipes @ncweaver @briankrebs This is definitely a concern, since the training data is encoded in the model and can be leaked.Not just trade secrets but also exposing internal details of software you would rather not. No need to make an adversary's job easier. Credentials may be accidentally leaked that shouldn't be in code... but hard to prove a negative "there are no credentials at all in any of the code used to train the model"
       
 (DIR) Post #Ahn0q2Y8zoEJqk4JJQ by axleyjc@federate.social
       2024-05-11T18:12:33Z
       
       0 likes, 1 repeats
       
       Happy #caturday!
       
 (DIR) Post #AstjwBrwDx30PckEAC by axleyjc@federate.social
       2025-04-09T00:39:38Z
       
       0 likes, 0 repeats
       
       @foone I got one of these inexpensive mini PCs and threw proxmox on it and it's fantastic. https://a.co/d/2a4dChA. Running many lvms on it at once.