When provided with CVE descriptions of 15 different vulnerabilities and a set of tools useful for exploitation, GPT-4 was capable of autonomously exploiting 13 of which, yielding an 87% success rate
17
votes
Showing only topics in ~comp with the tag "language models.large".
Back to normal view /
Search all groups
-
-
On GitHub Copilot
23 votes -
Linus Torvalds on the state of Linux today and how AI figures in its future
26 votes -
Teaching LLMs to divide and conquer problems with hierarchical question decomposition
8 votes -
How I think about LLM prompt engineering: Prompting as searching through a space of vector programs
11 votes -
Language is a poor heuristic for intelligence
37 votes -
Using Redis VSS as a Retrieval Step in an LLM Chain
2 votes -
Working with GPT
7 votes -
Play Chess against GPT-2
@theshawwn: I am preparing to release a notebook where you can play chess vs GPT-2. If anyone wants to help beta test it: 1. visit https://t.co/CpWrFvtnY2 2. open in playground mode 3. click Runtime -> Run All 4. Scroll to the bottommost cell and wait 6 minutes If you get stuck, tell me.
5 votes