history
30 articles about history in AI news
Amazon’s Alexa Now Shows 365-Day Price History for Shopping
Amazon expanded Alexa for Shopping to show 30, 90, and 365 days of price history. Over 50 million customers have used the feature since 2024, enhancing deal confidence.
CodeRabbit AI Absorbs Codebase History, Reduces 'Bus Factor' Risk
A developer's tweet highlights CodeRabbit's ability to remember a team's codebase history and past decisions, directly addressing the 'bus factor' problem of over-reliance on senior engineers.
How to Use Git History to Analyze Claude's System Prompt Evolution
A new tool converts Anthropic's official system prompt history into a git timeline, enabling developers to analyze prompt changes with standard version control commands.
MemRerank: A Reinforcement Learning Framework for Distilling Purchase History into Personalized Product Reranking
Researchers propose MemRerank, a framework that uses RL to distill noisy user purchase histories into concise 'preference memory' for LLM-based shopping agents. It improves personalized product reranking accuracy by up to +10.61 points versus raw-history baselines.
Codeset: Boost Claude Code's Task Success Rate by 10% with Project History
Codeset analyzes your git history to generate contextual docs that make Claude Code 10% more effective at completing coding tasks.
Alec Radford's 'Talk to the Past' AI Lets You Chat with History
A new AI project by Alec Radford and David Duvenaud lets you chat with simulated historical figures.
Overnight CLI: Train Claude Code on Your Own Chat History to Work While You Sleep
Overnight is a new open-source CLI that analyzes your Claude Code conversations to build a personal coding profile, then predicts and executes your next steps autonomously.
From Browsing History to Personalized Emails: Transformer-Based Product Recommendations
A technical article outlines a transformer-based system for generating personalized product recommendations from user browsing data, directly applicable to retail and luxury e-commerce for enhancing email marketing and on-site personalization.
The Trillion-Dollar Threshold: How AI and Space Tech Could Create History's First Trillionaire
Former Google executive Mo Gawdat predicts AI investments will create the world's first trillionaire before 2030, while SpaceX's potential 2026 IPO could propel Elon Musk toward that unprecedented wealth milestone through space-based technology.
Beyond Browsing History: How Promptable AI Can Decode Luxury Client Intent in Real-Time
A new AI framework, Decoupled Promptable Sequential Recommendation (DPR), merges collaborative filtering with LLM reasoning. It lets users steer product discovery via natural language prompts, enabling luxury retailers to respond instantly to explicit client desires while respecting their historical taste.
SoftBank's $40 Billion Bet: The Largest AI Investment Loan in History
SoftBank Group is seeking a record $40 billion loan primarily to finance its investment in OpenAI, marking the largest-ever dollar-denominated borrowing by the Japanese conglomerate. This massive financial move comes as OpenAI releases groundbreaking models like GPT-5.4 and shifts its commercial strategy.
Stop AI Refactors From Breaking Production: Add git log -L to Your CLAUDE.md
Add a git log -L rule to CLAUDE.md. It forces Claude Code to check commit history before editing existing code, cutting 'confident but wrong' refactors for ~6% overhead. The agent also writes why-comments back into the code, compounding the fix.
Git Hook + Claude Code: How to Force Your AI Agent to Write Commit
Enforce commit quality with a commit-msg hook, not prompts. This hard gate forces Claude Code to explain 'why', yielding atomic commits and a searchable git history.
Denim Tears' 153-Piece André Leon Talley Capsule Opens Archives
Denim Tears drops 153-piece André Leon Talley collection, opening its archive with collabs. The move reframes the brand's history as cultural storytelling.
How Claude Code scales to 500K+ line monorepos
Claude Code handles 500K+ line monorepos via hierarchical context management using AST parsing and git history, achieving 94% accuracy on multi-file edits.
Almanac: Open-Source Wiki Auto-Updates From Claude Code Chats
Almanac auto-generates a markdown wiki from Claude Code chats and repo history, solving the agent context gap. Free open-source tool, MacOS-only.
Meta: Code Agents Improve by Reusing Short Summaries, Not Raw Logs
Meta's new paper reveals that coding agents with summary-based history reuse outperform those using raw logs, improving efficiency and success on complex tasks.
ItemRAG: A New RAG Approach for LLM-Based Recommendation That Retrieves
ItemRAG shifts RAG for LLM-based recommenders from user-history retrieval to fine-grained item-level retrieval, using co-purchase and semantic data to prioritize informative items. Experiments show consistent outperformance over existing methods, especially for cold-start items.
HUOZIIME: A Research Framework for On-Device LLM-Powered Input Methods
A new research paper introduces HUOZIIME, a personalized on-device input method powered by a lightweight LLM. It uses a hierarchical memory mechanism to capture user-specific input history, enabling privacy-preserving, real-time text generation tailored to individual writing styles.
AgentPulse: The Open-Source Dashboard That Solves Claude Code's
Install AgentPulse to gain visibility into all your active Claude Code and Codex CLI sessions from a single web dashboard, with live updates, session naming, and prompt history.
DUET: A New LLM-Based Recommender That Generates Paired User-Item Profiles
A new research paper introduces DUET, an interaction-aware profile generator for recommendation systems. Instead of using dense vectors or independent text descriptions, it jointly creates semantically consistent user and item profiles conditioned on their interaction history, optimizing them with reinforcement learning for better performance.
FAVE: A New Flow-Based Method for One-Step Sequential Recommendation
A new arXiv paper introduces FAVE, a framework for sequential recommendation that uses a two-stage training strategy to learn a direct trajectory from a user's history to the next item. It promises high accuracy and dramatically faster inference, making it suitable for real-time applications.
How Claude Code's System Prompt Engine Actually Works
Claude Code builds its system prompt dynamically from core instructions, conditional tool definitions, user files, and managed conversation history, revealing the critical role of context engineering.
Unnamed Python Rewrite Gains 47K+ GitHub Stars in 5 Hours, Breaks Platform Velocity Record
An unidentified Python rewrite project amassed over 47,000 GitHub stars in just five hours, a velocity faster than any previous project in the platform's history. The viral surge suggests a high-demand tool or library, though its exact nature and technical merits remain unverified.
RCLRec: Reverse Curriculum Learning Targets Sparse Conversion Problem in Generative Recommendation
Researchers propose RCLRec, a reverse curriculum learning framework for generative recommendation that specifically addresses sparse conversion signals. By constructing short, conversion-focused curricula from user history, it provides targeted supervision, boosting online ad revenue by +2.09% and orders by +1.86%.
VISTA: A Novel Two-Stage Framework for Scaling Sequential Recommenders to Lifelong User Histories
Researchers propose VISTA, a two-stage modeling framework that decomposes target attention to scale sequential recommendation to a million-item user history while keeping inference costs fixed. It has been deployed on a platform serving billions.
Google Gemini Launches Manual Memory & Chat Import to Ease Switching from ChatGPT, Claude
Google Gemini is rolling out 'Import Memory' and 'Import Chat History' features for desktop users. The manual tools provide prompts and a .zip upload to transfer data from other AI assistants, aiming to lower the barrier for users to switch from competitors like ChatGPT or Claude.
Add Semantic Search to Claude Code with pmem: A Local RAG That Cuts Token Costs 75%
Install pmem, a local RAG MCP server, to give Claude Code instant semantic search over your entire project's history, slashing token usage for file retrieval.
RSES CLI: Hand Off Coding Sessions Between Claude Code, Codex, and OpenCode in One Command
RSES CLI lets you seamlessly transfer active coding sessions between Claude Code, Codex CLI, and OpenCode with a single command, preserving context and task history.
Building Sequential AI Workflows with Microsoft Agent Framework and Azure AI Foundry
A technical walkthrough of implementing a sequential agent workflow for security incident triage using Microsoft's Agent Framework and Azure AI Foundry. Demonstrates how to structure multi-stage AI processes where each agent builds on previous outputs with full conversation history.