HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
amarble
Born on March 20, 2021
•
156 Karma
About
Submitted
Comments
Favorites
Request
1.
There is minimal downside to switching to open models
marble.onl
33 comments
6 hours ago
amarble
78 points
2.
AI doesn't replace white collar work
marble.onl
104 comments
3 months ago
amarble
67 points
3.
I paid $170 and all I got was this demo
marble.onl
1 comment
4 months ago
amarble
3 points
4.
I paid $170 and all I got was this stupid demo
marble.onl
4 months ago
amarble
1 points
5.
Task-free intelligence testing of LLMs
marble.onl
22 comments
5 months ago
amarble
69 points
6.
Task-free intelligence testing of LLMs
marble.onl
5 months ago
amarble
1 points
7.
Intelligence is not just about task completion
marble.onl
5 months ago
amarble
1 points
8.
If You Meet ET in Space, Kill Him (2024)
nautil.us
5 months ago
amarble
3 points
9.
Intelligence is not just about task completion
marble.onl
5 months ago
amarble
3 points
10.
Show HN: Gen AI Writing Showdown
writing-showdown.com
6 months ago
amarble
2 points
11.
Ifrro member Kopinor signs agreement on newspaper content for AI in Norway
ifrro.org
6 months ago
amarble
2 points
12.
Comparing language model performance on creative writing transformations
writing-showdown.com
6 months ago
amarble
2 points
13.
Eminembench
marble.onl
8 months ago
amarble
1 points
14.
Promptware Attacks Against LLM-Powered Assistants in Production
sites.google.com
9 months ago
amarble
1 points
15.
Managing LLM application performance through code standards
marble.onl
on April 2, 2025
amarble
2 points
16.
Catching Claude Cheating
marble.onl
on March 25, 2025
amarble
1 points
17.
Catching Claude Cheating
marble.onl
1 comment
on March 23, 2025
amarble
1 points
18.
Scanning AI application code for vulnerabilities and performance issues
marble.onl
on March 20, 2025
amarble
3 points
19.
Show HN: A static scanner for LLM app code
github.com/kereva-dev
1 comment
on March 17, 2025
amarble
6 points
20.
Scanning AI application code for vulnerabilities and performance issues
marble.onl
on March 17, 2025
amarble
2 points
21.
The Model Trust Score: The Framework for Strategic Enterprise AI Model Selection
credo.ai
on March 4, 2025
amarble
2 points
22.
Evals are not all you need
marble.onl
12 comments
on March 3, 2025
amarble
58 points
23.
An AI Cyber Incident in Plain Sight
marble.onl
on Nov 24, 2024
amarble
2 points
24.
AI agent using Anthropic's tool calling and the Pandas Python library
github.com/rbitr
on Nov 13, 2024
amarble
2 points
25.
Following LLM Manufacturer's Instructions
armilla.ai
1 comment
on Oct 22, 2024
amarble
3 points
26.
AI Cybersecurity Lessons from GenAI
marble.onl
on June 22, 2024
amarble
1 points