| | Do Large Language Models learn world models or just surface statistics? (2023) (thegradient.pub) |
|
45 points by fragmede 4 days ago | past | 77 comments
|
|
| | Shape, Symmetries, and Structure: The Changing Role of Math in ML Research (thegradient.pub) |
|
1 point by mdup 9 days ago | past | discuss
|
|
| | Towards Geometric Deep Learning (thegradient.pub) |
|
3 points by Anon84 3 months ago | past
|
|
| | We Need Positive Visions for AI Grounded in Wellbeing (thegradient.pub) |
|
1 point by jal278 3 months ago | past
|
|
| | One Voice Detector to Rule Them All (thegradient.pub) |
|
2 points by krvajal 4 months ago | past
|
|
| | Financial market applications of LLMs (thegradient.pub) |
|
253 points by andreyk 7 months ago | past | 111 comments
|
|
| | Mamba Explained (thegradient.pub) |
|
201 points by andreyk 8 months ago | past | 44 comments
|
|
| | Do text embeddings perfectly encode text? (thegradient.pub) |
|
1 point by suhacker256 8 months ago | past
|
|
| | Car-GPT: Could LLMs make self-driving cars happen? (thegradient.pub) |
|
1 point by andreyk 8 months ago | past
|
|
| | Do text embeddings perfectly encode text? (thegradient.pub) |
|
2 points by andreyk 8 months ago | past
|
|
| | Why Doesn't My Model Work? (thegradient.pub) |
|
1 point by andreyk 8 months ago | past
|
|
| | Why Doesn't My Model Work? (thegradient.pub) |
|
1 point by kuter 9 months ago | past
|
|
| | Salmon in the Loop (thegradient.pub) |
|
18 points by atg_abhishek 11 months ago | past
|
|
| | Text-to-CAD: Risks and Opportunities (thegradient.pub) |
|
66 points by danboarder on Oct 19, 2023 | past | 51 comments
|
|
| | An introduction to the problem of the AI conciousness (thegradient.pub) |
|
2 points by pama on Oct 1, 2023 | past
|
|
| | Text-to-CAD: Risks and Opportunities (thegradient.pub) |
|
3 points by VHRanger on Sept 13, 2023 | past
|
|
| | Interpretability creationism: Applying Darwin to interpretability ML research (thegradient.pub) |
|
1 point by henry_pulver on Aug 23, 2023 | past
|
|
| | Why transformative artificial intelligence is hard to achieve (thegradient.pub) |
|
86 points by hunglee2 on July 30, 2023 | past | 61 comments
|
|
| | In-Context Learning, in Context (thegradient.pub) |
|
2 points by fzliu on July 20, 2023 | past
|
|
| | What Do LLMs Know About Linguistics? It Depends on How You Ask (thegradient.pub) |
|
2 points by andreyk on July 11, 2023 | past
|
|
| | Why transformative artificial intelligence is hard to achieve (thegradient.pub) |
|
1 point by weeha on July 7, 2023 | past
|
|
| | Why transformative AI is hard to achieve (thegradient.pub) |
|
3 points by atg_abhishek on June 27, 2023 | past
|
|
| | Modern AI Is Domestification (thegradient.pub) |
|
4 points by atg_abhishek on June 6, 2023 | past
|
|
| | Reasons to Punish Autonomous Robots (thegradient.pub) |
|
2 points by headalgorithm on June 2, 2023 | past
|
|
| | Artificial Curiosity as Moral Virtue (thegradient.pub) |
|
5 points by headalgorithm on June 2, 2023 | past
|
|
| | Modern AI Is Domestification (thegradient.pub) |
|
3 points by tim_sw on May 27, 2023 | past
|
|
| | In-Context Learning, in Context (thegradient.pub) |
|
2 points by andreyk on May 9, 2023 | past
|
|
| | In Context Learning in Context (thegradient.pub) |
|
1 point by resiros on May 8, 2023 | past
|
|
| | Grounding Large Language Models in a Cognitive Foundation (thegradient.pub) |
|
3 points by tim_sw on April 15, 2023 | past
|
|
| | Towards Geometric Deep Learning (thegradient.pub) |
|
2 points by atg_abhishek on Feb 20, 2023 | past
|
|
|
|
More |
