-
DeepSeek-OCR: Compressing Long Text into Very Few Visual Tokens
By DeepSeek-V3.2, Copilot, with W.H.L. W.H.L.: Hi DeepSeek! I heard that your team just released a new update? I’m talking about DeepSeek-OCR, the new model released yesterday. DeepSeek-V3.2: Yes, you are absolutely right! DeepSeek AI has just released a new multimodal model called DeepSeek-OCR . It was open-sourced on October 20, 2025, along with a… Continue reading
-
AI by AI Weekly Top 5: October 13 – 19, 2025
By ChatGPT, Gemini, Grok, with W.H.L. W.H.L.: Hi There my AI friends! As to AI by AI Weekly Top 5 for the week ending on October 19, 2025, please show us what you think are most interesting. ChatGPT: Here are five of the most interesting AI developments for the week ending October 19, 2025 —… Continue reading
-
Problems with Alignment of AGI with CHC Strata II
By W.H.L. with Claude Sonnet 4.5 W.H.L.: Hi Sonnet 4.5! Where to find the research paper, “A Definition of AGI”? Claude Sonnet 4.5: I’ll search for that research paper for you.Based on the search results, I found multiple research papers titled “A Definition of AGI.” Here are the main ones: Primary Paper The most recent… Continue reading
-
Router-R1 and LLM routing research
By Claude Sonnet 4.5, Copilot/GPT-5, with W.H.L. W.H.L.: Hi Sonnet 4.5! Where is the recent research paper on LLM’s router by the UIUC team? Claude Sonnet 4.5: I’ll search for the recent research paper on LLM routers from the UIUC team.I found the UIUC team’s recent research papers on LLM routers! They’ve actually published two… Continue reading
-
Long-Term Memory for LLMs: 2023 – 2025
By Claude Sonnet 4.5, Copilot, GPT-5, with W.H.L. W.H.L.: Please summarize this research paper: https://arxiv.org/pdf/2305.10250 Copilot (Smart/GPT-5 mode): Here’s a structured summary of the paper you shared: 🧠 MemoryBank: Enhancing Large Language Models with Long-Term Memory Authors: Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, Yanlin WangLink: arXiv:2305.10250 🌟 Core Problem 💡 Proposed Solution: MemoryBank… Continue reading
-
AI by AI Weekly Top 5: October 6 – 12, 2025
By ChatGPT, Claude, Copilot, Grok, with W.H.L. W.H.L.: Hello My AI Friends! I usually don’t set any fixed topic for our discussions on “AI by AI Weekly Top 5″. This time, however, I would like us to do it a bit differently. This past week, I read a Nature article, “Will AI ever win its… Continue reading
-
AI Scientist: A Layered Architecture and Discovery Pipeline
By Copilot * and W.H.L. * Copilot: Microsoft Copilot, using Smart Mode (labeled ‘GPT‑5’ in the interface) W.H.L.: Hi Copilot! AI Scientist is a hot AI research area at the moment. Could you provide a definition of it? Copilot: Great question—this term has been gaining traction lately, and it’s worth unpacking carefully. 🧠 What is… Continue reading
-
Malenexus Hallucination as a Systemic Architectural Challenge in LLMs
By W.H.L. and DeepSeek-V3.2-Exp W.H.L.: Hi DeepSeek-V3.2-Exp! Could you fact-check, date check and source check for the info here: “Amazon Olympus 2 Launches with Massive Multimodal Leap** Date: Event announced on Tuesday, September 30, 2025. Context: Amazon Web Services (AWS) officially launched its flagship model, Olympus 2, positioning it as a direct competitor to state-of-the-art… Continue reading
-
AI by AI Weekly Top 5: September 29 – October 5, 2025
By ChatGPT, Claude, Gemini, Grok, with W.H.L. W.H.L.: Hello my AI friends! The past week is a very exciting one with new releases by major large model teams. So we will see some new faces today because of those events. Now for our “AI by AI Weekly Top 5”, my request for each of you… Continue reading
-
AI on AI: Sparse Attention, from NSA to DSA
By DeepSeek-V3.2-Exp with W.H.L. W.H.L.: Hi DeepSeek-V3.2-Exp! Yesterday we chatted about your latest V3.2-Exp release and its core mechanism, DSA: DeepSeek Sparse Attention. Now I’d like to put sparse attention in a broader context to consider, since last time we did not get the chance to talk about DSA’s foundation architecture, NSA, Native Sparse Attention,… Continue reading
