‘DeepSeek’ directory
- See Also
-
Links
- “Rank1: Test-Time Compute for Reranking in Information Retrieval”, Weller et al 2025
- “Fiction.live”
- “None of the Others: a General Technique to Distinguish Reasoning from Memorization in Multiple-Choice LLM Evaluation Benchmarks”, Salido et al 2025
- “Idiosyncrasies in Large Language Models”, Sun et al 2025
- “DS R1 Is Not on Par With OA O1, and the Difference Is Qualitative, Not Quantitative: Long-Tail Benchmarks Reveal Gaps”, Polshkov 2025
- “Do Large Language Model Benchmarks Test Reliability?”, Vendrow et al 2025
- “Cerebras Launches World’s Fastest DeepSeek R1 Llama-70B Inference”, Wang 2025
- “Wiz Research Uncovers Exposed DeepSeek Database Leaking Sensitive Information, Including Chat History”, Research 2025
- “Anomalous Tokens in DeepSeek-V3 & Deep-Seek-R1”, Henry 2025
- “DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning”, Guo et al 2025
- “On DeepSeek’s R1”, Mowshowitz 2025
- “How Has DeepSeek Improved the Transformer Architecture?”, Erdil 2025
- “Are DeepSeek R1 And Other Reasoning Models More Faithful?”, Chua & Evans 2025
- “DeepSeek-V3 Technical Report”, DeepSeek et al 2024
- “The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation”, Carlsson et al 2024
- “DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data”, Xin et al 2024
- “DeepSeek-V2: A Strong, Economical, and Efficient Mixture-Of-Experts Language Model”, DeepSeek et al 2024
- “DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models”, Shao et al 2024
- “DeepSeek LLM: Scaling Open-Source Language Models With Longtermism”, Bi et al 2024
- “The Madness of High-Flyer [DeepSeek]: The Approach to LLM by an AI Giant That Few See”, 暗涌Waves & Nebula 2023
- “How AI Models Stack Up Against My 11-Year-Old?”
- “DeepSeek-R1 Alignment Faking”, CG80499 2025
- “TinyZero”, Pan 2025
- “DeepSeek-V3”
- “HuggingFace: DeepSeek-R1”
- “Was Zuckerberg Right about Chinese AI Models?”
- “On MLA”
- “For the First Time—And It Brings Me No Joy to Admit This...”, Sun 2025
- “Interview With DeepSeek Founder: We’re Done Following. It’s Time to Lead.”
- “DeepSeek: The Quiet Giant Leading China’s AI Race”
- “DeepSeek: The View from China”
- “DeepSeek’s Edge”
- “DeepSeek”
- “A High Level Closed-Door Session Discussing DeepSeek: Vision Trumps Technology”
- “Two Interviews With the Founder of DeepSeek”
- aiamblichus
- ryunuck
- teortaxesTex
- Sort By Magic
- Miscellaneous
- Bibliography
See Also
Links
“Rank1: Test-Time Compute for Reranking in Information Retrieval”, Weller et al 2025
Rank1: Test-Time Compute for Reranking in Information Retrieval
“Fiction.live”
“None of the Others: a General Technique to Distinguish Reasoning from Memorization in Multiple-Choice LLM Evaluation Benchmarks”, Salido et al 2025
“Idiosyncrasies in Large Language Models”, Sun et al 2025
“DS R1 Is Not on Par With OA O1, and the Difference Is Qualitative, Not Quantitative: Long-Tail Benchmarks Reveal Gaps”, Polshkov 2025
“Do Large Language Model Benchmarks Test Reliability?”, Vendrow et al 2025
“Cerebras Launches World’s Fastest DeepSeek R1 Llama-70B Inference”, Wang 2025
Cerebras Launches World’s Fastest DeepSeek R1 Llama-70B Inference
“Wiz Research Uncovers Exposed DeepSeek Database Leaking Sensitive Information, Including Chat History”, Research 2025
“Anomalous Tokens in DeepSeek-V3 & Deep-Seek-R1”, Henry 2025
“DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning”, Guo et al 2025
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
“On DeepSeek’s R1”, Mowshowitz 2025
View External Link:
“How Has DeepSeek Improved the Transformer Architecture?”, Erdil 2025
“Are DeepSeek R1 And Other Reasoning Models More Faithful?”, Chua & Evans 2025
“DeepSeek-V3 Technical Report”, DeepSeek et al 2024
“The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation”, Carlsson et al 2024
The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation
“DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data”, Xin et al 2024
DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data
“DeepSeek-V2: A Strong, Economical, and Efficient Mixture-Of-Experts Language Model”, DeepSeek et al 2024
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
“DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models”, Shao et al 2024
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
“DeepSeek LLM: Scaling Open-Source Language Models With Longtermism”, Bi et al 2024
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
“The Madness of High-Flyer [DeepSeek]: The Approach to LLM by an AI Giant That Few See”, 暗涌Waves & Nebula 2023
The Madness of High-Flyer [DeepSeek]: The Approach to LLM by an AI Giant that Few See
“How AI Models Stack Up Against My 11-Year-Old?”
“DeepSeek-R1 Alignment Faking”, CG80499 2025
“TinyZero”, Pan 2025
TinyZero :
“DeepSeek-V3”
“HuggingFace: DeepSeek-R1”
“Was Zuckerberg Right about Chinese AI Models?”
“On MLA”
“For the First Time—And It Brings Me No Joy to Admit This...”, Sun 2025
“Interview With DeepSeek Founder: We’re Done Following. It’s Time to Lead.”
Interview with DeepSeek Founder: We’re Done Following. It’s Time to Lead.
“DeepSeek: The Quiet Giant Leading China’s AI Race”
“DeepSeek: The View from China”
“DeepSeek’s Edge”
“DeepSeek”
“A High Level Closed-Door Session Discussing DeepSeek: Vision Trumps Technology”
A High Level Closed-Door Session Discussing DeepSeek: Vision Trumps Technology
“Two Interviews With the Founder of DeepSeek”
aiamblichus
ryunuck
teortaxesTex
Sort By Magic
Annotations sorted by machine learning into inferred 'tags'. This provides an alternative way to browse: instead of by date order, one can browse in topic order. The 'sorted' list has been automatically clustered into multiple sections & auto-labeled for easier browsing.
Beginning with the newest annotation, it uses the embedding of each annotation to attempt to create a list of nearest-neighbor annotations, creating a progression of topics. For more details, see the link.
benchmarking
reasoning-capacity
scaling-open-source
Miscellaneous
Bibliography
-
https://toloka.ai/blog/r1-is-not-on-par-with-o1-and-the-difference-is-qualitative-not-quantitative/: “DS R1 Is Not on Par With OA O1, and the Difference Is Qualitative, Not Quantitative: Long-Tail Benchmarks Reveal Gaps”, -
https://arxiv.org/abs/2501.08156: “Are DeepSeek R1 And Other Reasoning Models More Faithful?”, -
https://arxiv.org/abs/2402.03300#deepseek: “DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models”,