Topics Pioneers Insight Method Author

CTRL K

Switch to Chinese

Light
Dark
System

Topics Pioneers Insight Method Author

Topics
Insight
Method
Author
Pioneers

Switch to Chinese

Light
Dark
System

Long Context and External Memory Bottlenecks

Addresses inherent scaling limits of context windows and retrieval-ranking bottlenecks in long-term external memory.

0 sources

Voices in this topic

Harrison Chase Alex Zhang Eric Bigelow Alexander Wissner-Gross Ed H. Chi（纪怀新） Ed H. Chi

All paragraphs

Oct 19, 2026

硅谷坐标 Silicon Valley Vector Google DeepMind's Ed Chi: AI's Endgame Is Capability Over Cost

Ed H. Chi Memory is a bottleneck that researchers have yet to fully understand: Transformer context buffers can currently reach around 1 million or 2 million tokens, which he considers nowhere near enough. His core framework is that memory is not just storage and retrieval; it is also a ranking problem—when you think of Paris, which memories …

Oct 18, 2026

硅谷坐标 Silicon Valley Vector DeepMind's Ed Chi: Future of Personalized General-Purpose Assistants

Ed H. Chi（纪怀新） Memory is an underappreciated bottleneck, and it involves ranking as well as storage and retrieval. Transformer context buffers of 1–2 million tokens are nowhere near enough, in his view; from a cognitive perspective, memory is also a kind …

Oct 17, 2026

20VC LangChain's Chase: vertical agents win, routing lives in the harness

Harrison Chase Memory is the biggest unsolved layer in agents, and LangChain has the scar tissue to prove it. The hard part isn't the database (some companies store memory in "a single file") but distilling observations into context — a …

Oct 15, 2026

Moonshots OpenAI Bulk-Solves 722 Math Problems, Anthropic’s Cruelty Policy, & Elon’s Quadrillion-Dollar SpaceX

Alexander Wissner-Gross On Meta's Muse Wonder launch, the panel splits: Gary Tan and Salim think Meta's 3.6B daily users plus "active memory" can win, while Alex says "almost nothing" impressed him — Wonder may sit near Sonnet 5.5/Opus 5.5 on raw capability, "but if you pay attention to cost, actually it's below the frontier," and Meta is speed-running OpenAI's lesson that revenue lives in enterprise, not consumer sycophancy. Salim's investor frame: "the next trillion dollar battle is not which AI is smartest, it's which one knows you best" — memory lock-in …

Oct 10, 2026

The Cognitive Revolution How Agents Decide: Goodfire's Eric Bigelow on Critical Tokens, Phase Shifts, & In-Context Learning

Eric Bigelow Bigelow expects context engineering, memory, and agent harnesses to outrun per-user fine-tuning in the near term. His broad definition of in-context learning covers every runtime representation change, including conversations, stories, reasoning traces, …

Oct 2, 2026

Latent Space Recursive Language Models — Alex Zhang, MIT PhD

Alex Zhang Zhang thinks Claude Code, Codex, Pi, and most current harnesses are variations of the same “trajectory as a prompt” loop. RLM is his counterexample: unload context into a persistent environment, let the model manipulate it through code, and recursively call …

Sharp Tech Preview: All About Agents — Dots Arrive Before OpenAI Is Ready

Sharp Tech Effective agents need fresh, task-specific context and durable external records—not one enormous conversation. Ben argues that million-token context “sucks” when old instructions become buried; his preferred system continually writes things down, …

Related topics

Specialized SLMs vs General LLMs Personal AI Assistants Adoption and Monetization AI Inference Cost Optimization

Switch to Chinese

Light
Dark
System

本站累计访问量：

© 2026 ZJ Deeper