Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
1.
Show HN: Langur – consistent, observable LLM agents (github.com/anerli)
1 point
anerli
2 years ago
discuss
2.
Can LLMs accurately evaluate their own confidence? (github.com/anerli)
2 points
anerli
a year ago
2 comments
3.
Show HN: Magnitude – open-source, AI-native test framework for web apps (github.com/magnitudedev)
179 points
anerli
a year ago
44 comments
4.
Show HN: Magnitude – Open-source AI browser automation framework (github.com/magnitudedev)
145 points
anerli
a year ago
40 comments
5.
Pure-vision browser agent scores 94% on WebVoyager (SOTA) (github.com/magnitudedev)
5 points
anerli
a year ago
1 comment
6.
Show HN: Magnitude MCP – vision-first browser interaction for Claude Code (github.com/sagekit)
2 points
anerli
8 months ago
discuss
7.
Aneris: Program logic for developing and verifying distributed systems (github.com/logsem)
4 points
todsacerdoti
4 years ago
discuss