-
Урок 1.
00:16:48
01. Lecture 0. Introductions
-
Урок 2.
00:26:19
02. Lecture 1. Synthetic data, fake it until you make it
-
Урок 3.
00:12:43
03. Week 1 - 1 Synthetic Questions
-
Урок 4.
00:13:24
04. Week 1 - 2 Benchmarking Retrieval
-
Урок 5.
00:09:01
05. Week 1 - 3 Statistical Validation
-
Урок 6.
00:19:36
06. Introductions
-
Урок 7.
00:47:33
07. Office Hours MAY 20
-
Урок 8.
00:52:08
08. Understanding Embedding Performance through Generative Evals [Kelly Hong]
-
Урок 9.
00:51:11
09. Semantic search over the web with Exa [Will Bryk]
-
Урок 10.
00:54:57
010. Office Hour MAY 22
-
Урок 11.
00:19:40
011. Optional Notebook Office Hour MAY 22
-
Урок 12.
00:53:28
012. Online Evals and Production Monitoring [Ben Hylak & Sidhant Bendre]
-
Урок 13.
00:54:38
013. Data is Everything Finding needles in multimodal haystacks [Rajan Agarwal & Luke Igel]
-
Урок 14.
00:57:36
014. Week 2 Office Hour MAY 27
-
Урок 15.
00:38:56
015. Week 2 Office Hour MAY 29
-
Урок 16.
00:44:08
016. Optional Notebook Office Hour MAY 29
-
Урок 17.
00:24:15
017. Lecture 3 Product UX Feedback
-
Урок 18.
00:50:58
018. Latency First How to Actually Make RAG & Agents Fast [Aarush Sah] JUNE 4
-
Урок 19.
00:51:54
019. Week 3 RAG Without APIs When Function Calling Talks to Your Browser [Michael Struwig]
-
Урок 20.
00:33:25
020 Office Hour June 5
-
Урок 21.
00:34:59
021 Lecture 4 Segmentation - Descript
-
Урок 22.
00:11:57
022 Week 4 - 1 Generate Dataset - Descript
-
Урок 23.
00:09:33
023 Week 4 - 2 Topic Modelling - Descript
-
Урок 24.
00:03:02
024 Week 4 - 3 Classifier - Descript
-
Урок 25.
00:51:10
025 RAG Anti-patterns in the Wild, and How to Fix Them [Skylar Payne]
-
Урок 26.
00:53:15
026 Office Hour JUNE 10
-
Урок 27.
00:41:44
027 Office Hour JUNE 12
-
Урок 28.
00:30:27
028 Lecture 5 Multimodality - Descript
-
Урок 29.
00:06:48
029 Week 5 - 1 Generate Dataset - Descript
-
Урок 30.
00:13:33
030 Week 5 - 2 Metadata Filtering - Descript
-
Урок 31.
00:10:45
031 Week 5 - 3 Text-2-SQL - Descript
-
Урок 32.
00:10:59
032 Week 5 - 4 PDF-Parser - Descript
-
Урок 33.
00:07:30
033 Week 5 - 4 Cohere Embed V4 - Descript
-
Урок 34.
00:52:40
034 Natural Language Search on Semi-Structured Data [Daniel Svonava]
-
Урок 35.
00:53:13
035 Better RAG Through Better Data [Adit Abraham]
-
Урок 36.
00:41:10
036 Office Hour JUNE 17
-
Урок 37.
00:51:58
037 Office Hour JUNE 19
-
Урок 38.
00:19:06
038 Lecture 6_ Routing - Descript
-
Урок 39.
00:06:51
039 Week 6 - 1 _ Evaluate Tools - Descript
-
Урок 40.
00:13:33
040 Week 6 - 2 _ Generate Dataset - Descript
-
Урок 41.
00:05:46
041 Week 6 - 3 _ Improving Performance - Descript
-
Урок 42.
00:53:49
042 RAG in the age of agents. SWE-Bench as a case study. [Colin Flaherty]
-
Урок 43.
00:55:25
043 How to Build Self-Improving AI via Data-Driven Loops [Hamish Ogilvy]
-
Урок 44.
01:05:31
044 Conclusions
-
Урок 45.
00:53:37
045 Improving retrievers by Reranking and embedding fine-tuning [Ayush Chaurasia]
-
Урок 46.
00:56:52
046 Lessons on retrieval for autonomous coding agents [Nik Pash]
-
Урок 47.
00:53:30
047 Startups to F500 Document Automation Lessons at Scale [Eli Badgio]
-
Урок 48.
00:52:20
048 Why Devin does not use multi agents [Walden Yan]
-
Урок 49.
00:49:26
049 Scaling Judge-Time Compute for Robust Auto LLM Evaluation [Leonard Tang]
-
Урок 50.
00:52:53
050 Rethinking RAG from first principles for agents [Beyang Liu]
It wasn’t easy, but we made it through. Thank you to everyone who took part in the campaign. Enjoy your learning!
I see there are a few participants are yet to pay and I can replace someone if needed..
Thanks..
Динамика складывается оптимистично. Присоединяйтесь!