1+ [
2+ {
3+ "title" : " How to build a better AI benchmark" ,
4+ "link" : " https://www.technologyreview.com/2025/05/08/1116192/how-to-build-a-better-ai-benchmark/" ,
5+ "date" : " 2025-05-08" ,
6+ "source" : " MIT Technology Review"
7+ },
8+ {
9+ "title" : " SWE-bench with John Yang and Carlos E. Jimenez - Weaviate Podcast #107!" ,
10+ "link" : " https://www.youtube.com/watch?v=8rwHAR4fsFg&pp=ygUJc3dlLWJlbmNo" ,
11+ "date" : " 2024-10-30" ,
12+ "source" : " Weaviate Podcast" ,
13+ "video" : true
14+ },
15+ {
16+ "title" : " SWE-Bench authors reflect on the state of LLM agents at Neurips 2024" ,
17+ "link" : " https://www.youtube.com/watch?v=bivZWNQHRfE&pp=ygUJc3dlLWJlbmNo" ,
18+ "date" : " 2025-01-13" ,
19+ "source" : " Jay Alammar" ,
20+ "video" : true
21+ },
22+ {
23+ "title" : " SWE bench & SWE agent | Data Brew | Episode 44" ,
24+ "link" : " https://www.youtube.com/watch?v=LgONGe838D0" ,
25+ "date" : " 2025-04-17" ,
26+ "source" : " Databricks" ,
27+ "video" : true
28+ },
29+ {
30+ "title" : " John Yang - SWE-bench: Can Language Models Resolve Real-World GitHub Issues?" ,
31+ "link" : " https://www.youtube.com/watch?v=DrLdvbkgmeA&pp=ygUJc3dlLWJlbmNo" ,
32+ "date" : " 2023-11-03" ,
33+ "source" : " Rohan Alexander" ,
34+ "video" : true
35+ },
36+ {
37+ "title" : " AI Agent Automatically Codes WITH TOOLS - SWE-Agent Tutorial" ,
38+ "link" : " https://www.youtube.com/watch?v=9-JBHGlYEBI&list=PLhjeIHf6kJlUTPdUDDh3rLbaBT7-uRwa0&index=1&pp=iAQB" ,
39+ "date" : " 2024-04-05" ,
40+ "source" : " Matthew Berman" ,
41+ "video" : true
42+ },
43+ {
44+ "title" : " SWE-agent: A deep dive" ,
45+ "link" : " https://www.youtube.com/watch?v=RJ6NN8Y-xok" ,
46+ "date" : " 2024-04-02" ,
47+ "source" : " Ofir Press" ,
48+ "video" : true
49+ },
50+ {
51+ "title" : " A First Look at SWE-agent" ,
52+ "link" : " https://www.youtube.com/watch?v=CeMtJ4XObAM" ,
53+ "date" : " 2024-04-01" ,
54+ "source" : " Carlos E. Jimenez" ,
55+ "video" : true
56+ },
57+ {
58+ "title" : " NeurIPS Hacker Cup AI: SWEAgent" ,
59+ "link" : " https://www.youtube.com/watch?v=d9gcXpiiDao" ,
60+ "date" : " 2024-08-15" ,
61+ "source" : " Weights & Biases" ,
62+ "video" : true
63+ },
64+ {
65+ "title" : " Autonomous Coding Agents, Instability at Stability AI, Mamba Mania, What Users Do With GenAI" ,
66+ "link" : " https://www.deeplearning.ai/the-batch/issue-244/" ,
67+ "date" : " 2024-04-10" ,
68+ "source" : " DeepLearning.AI"
69+ },
70+ {
71+ "title" : " I glimpsed the future of coding" ,
72+ "link" : " https://link.wired.com/public/36091943" ,
73+ "date" : " 2024-07-18" ,
74+ "source" : " Wired"
75+ },
76+ {
77+ "title" : " The AI-Powered Future of Coding Is Near" ,
78+ "link" : " https://www.wired.com/ai-powered-coding/" ,
79+ "date" : " 2024-07-18" ,
80+ "source" : " Wired"
81+ },
82+ {
83+ "title" : " Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet" ,
84+ "link" : " https://www.anthropic.com/engineering/swe-bench-sonnet" ,
85+ "date" : " 2025-01-06" ,
86+ "source" : " Anthropic"
87+ },
88+ {
89+ "title" : " AI models still struggle to debug software, Microsoft study shows" ,
90+ "link" : " https://techcrunch.com/2025/04/10/ai-models-still-struggle-to-debug-software-microsoft-study-shows/" ,
91+ "date" : " 2025-04-10" ,
92+ "source" : " TechCrunch"
93+ }
94+ ]
0 commit comments