All
5+
10+
25+
50+
100+
5
Pure-vision browser agent scores 94% on WebVoyager (SOTA) (github.com/magnitudedev)
2 weeks ago |
anerli
| github.com
|
newest
35
Show HN: Magnitude – Open-source AI browser automation framework (github.com/magnitudedev)
3 weeks ago |
anerli
| github.com
|
best
3
Parallel Scaling Law for Language Models (arxiv.org)
2 months ago |
anerli
| arxiv.org
|
newest
58
Show HN: Magnitude – open-source, AI-native test framework for web apps (github.com/magnitudedev)
3 months ago |
anerli
| github.com
|
best
4
Can LLMs accurately evaluate their own confidence? (github.com/anerli)
4 months ago |
anerli
| github.com
|
newest
3
Will AI Ruin Your Codebase? (magnitude.run)
5 months ago |
anerli
| magnitude.run
|
newest
2
Why LLM Agents Today Don't Work (langur.ai)
8 months ago |
anerli
| langur.ai
|
newest
1
Show HN: Langur – consistent, observable LLM agents (github.com/anerli)
8 months ago |
anerli
| github.com
|
newest