Format Online paper / PDF "Chain-of-thought rationales can be misleading and are neither necessary nor sufficient for trustworthy interpretability." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Can We Automate Uncertainty? Source title Chain-of-Thought Is Not Explainability Source authors Fazl Barez et al. Source year 2025 Confidence high Importance high
Format Online paper / PDF "Chain-of-thought prompting allows language models to generate intermediate reasoning steps before producing a final answer." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Can We Automate Uncertainty? Source title Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Source authors Jason Wei et al. Source year 2022 Confidence high Importance mid
Format Online paper / PDF "Tree-search approaches let language models generate, evaluate and explore alternative reasoning paths." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Can We Automate Uncertainty? Source title Tree of Thoughts: Deliberate Problem Solving with Large Language Models Source authors Shunyu Yao et al. Source year 2023 Confidence high Importance mid
Format Web Page "Sequential agent workflows can process the output of one language-model call as input to another and introduce programmatic checks between steps." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Can We Automate Uncertainty? Source title Building effective agents Source authors Anthropic Source year 2024 Confidence high Importance mid
Format Web Page "Agentic systems augment language models with retrieval, tools and memory, allowing them to interact with external information and software." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Can We Automate Uncertainty? Source title Building effective agents Source authors Anthropic Source year 2024 Confidence high Importance mid
Format Web Page "One technical move around agentic systems is to braid language model outputs together through sequential processing and other orchestration patterns." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Can We Automate Uncertainty? Source title Building effective agents Source authors Anthropic Source year 2024 Confidence high Importance high
Format Web Page "AutoGPT helped popularise the autonomous AI harness and agent-loop approach in 2023." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Can We Automate Uncertainty? Source title AutoGPT Source authors Significant Gravitas Source year 2023 Confidence high Importance mid
Format Web Page "BabyAGI helped popularise early autonomous LLM agent loops in 2023." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Can We Automate Uncertainty? Source title BabyAGI Source authors Yohei Nakajima Source year 2023 Confidence high Importance mid
Format Tweet "Steven Sinofsky contrasts defined compiler mappings from machine code through higher-level languages with LLM code generation that begins from less precisely specified natural-language instructions." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Are Your Abstractions Managed? Source title One of the things not being discussed enough the history and context of LLM code generation Source authors Steven Sinofsky Source year 2024 Confidence mid Importance high
Format Web Page "Simon Willison highlighted varying load and batch size as a key source of nondeterminism in LLM inference endpoints." View Source Location PART 3 - THE THIRD AXIS CHAPTER 15: DEPLOY NOW, PRAY LATER Are Your Abstractions Managed? Source title Defeating Nondeterminism in LLM Inference Source authors Simon Willison Source year 2025 Confidence high Importance mid
