| | Interviewing Louis Castricato of Synth Labs and Eleuther AI on RLHF (interconnects.ai) |
| 4 points by lcastricato on March 4, 2024 | past | 1 comment |
|
| | Why reward models are key for alignment (interconnects.ai) |
| 3 points by headalgorithm on Feb 14, 2024 | past |
|
| | Open Language Models (OLMos) and the LLM Landscape (interconnects.ai) |
| 4 points by jasondavies on Feb 1, 2024 | past |
|
| | Model merging lessons in The Waifu Research Department (interconnects.ai) |
| 3 points by Philpax on Jan 29, 2024 | past |
|
| | RLHF Learning Resources in 2024 (interconnects.ai) |
| 3 points by sebg on Jan 18, 2024 | past |
|
| | Multimodal LM roundup: Unified IO 2, I/O, Gemini, LLaVA-RLHF, and RLHF questions (interconnects.ai) |
| 3 points by vsreekanti on Jan 10, 2024 | past |
|
| | State-space LLMs: Do we need Attention? (interconnects.ai) |
| 2 points by gardenfelder on Dec 20, 2023 | past | 1 comment |
|
| | Q* Hypothesis: Enhancing Reasoning, Rewards, and Synthetic Data (interconnects.ai) |
| 107 points by Jimmc414 on Nov 24, 2023 | past | 63 comments |
|
| | RLHF progress: Scaling DPO to 70B, DPO vs. PPO update, Tülu 2, Zephyr-β (interconnects.ai) |
| 2 points by EvgeniyZh on Nov 22, 2023 | past |
|
| | How the Foundation Model Transparency Index Distorts Transparency (interconnects.ai) |
| 1 point by swyx on Nov 15, 2023 | past |
|
| | LLMs Are Computing Platforms (interconnects.ai) |
| 2 points by vishnumenon on Oct 12, 2023 | past |
|
| | The AI research job market (interconnects.ai) |
| 207 points by sebg on Oct 12, 2023 | past | 183 comments |
|
| | The AI research job market shit show (interconnects.ai) |
| 2 points by tim_sw on Oct 11, 2023 | past |
|
| | How the open-source LLM ecosystem and leaderboards work (interconnects.ai) |
| 1 point by tim_sw on Sept 13, 2023 | past |
|
| | Specifying Objectives in RLHF (interconnects.ai) |
| 1 point by tim_sw on Aug 2, 2023 | past |
|
| | Llama 2: an open-source LLM (interconnects.ai) |
| 44 points by tim_sw on July 18, 2023 | past | 5 comments |
|
| | How RLHF Works (interconnects.ai) |
| 165 points by natolambert on June 21, 2023 | past | 32 comments |
|
| | Different Development Paths of LLMs (interconnects.ai) |
| 1 point by natolambert on June 15, 2023 | past |
|
| | Evaluating and Uncovering Open LLMs (interconnects.ai) |
| 2 points by headalgorithm on June 2, 2023 | past |
|
| | Evaluating and Uncovering Open LLMs (interconnects.ai) |
| 1 point by natolambert on May 31, 2023 | past |
|
| | Code: Green Pastures for LLMs (interconnects.ai) |
| 2 points by tim_sw on May 25, 2023 | past |
|
| | Unfortunately, OpenAI and Google have moats (interconnects.ai) |
| 3 points by headalgorithm on May 19, 2023 | past |
|
| | Unfortunately, OpenAI and Google have moats (interconnects.ai) |
| 2 points by natolambert on May 17, 2023 | past |
|
| | Specifying Hallucinations of LLMs (interconnects.ai) |
| 1 point by natolambert on May 3, 2023 | past |
|
| | Beyond human data: RLAIF needs a rebrand (interconnects.ai) |
| 1 point by tim_sw on April 26, 2023 | past |
|
