Author

AI Engineering

Focused on cutting‑edge product and technology information and practical experience sharing in the AI field (large models, MLOps/LLMOps, AI application development, AI infrastructure).

317

Articles

Likes

2.9k

Views

Comments

Latest from AI Engineering

100 recent articles max

AI Engineering

Oct 5, 2026 · Artificial Intelligence

Why AI Agents Need Documentation, Not Memory: A Critique of RAG-Based Memory Plugins

The article critiques typical RAG-based memory plugins for AI agents, highlighting five fundamental flaws—similarity retrieval ignores correctness, fragments lose context, outdated facts persist, agents cannot recognize knowledge gaps, and storage is unauditable—and proposes a documentation-centric approach where agents read and write Markdown files in a structured workspace, exemplified by the open-source Operator Memory plugin.

AI AgentsDocumentationOperator Memory

0 likes · 8 min read

Why AI Agents Need Documentation, Not Memory: A Critique of RAG-Based Memory Plugins

AI Engineering

Oct 4, 2026 · Databases

Semantic Filtering in Postgres Without Vector Indexes: pg-jev Hands-On

pg-jev is a PostgreSQL extension that wraps TypeSafe's Jev library into SQL functions, enabling semantic classification, probability scoring, and label selection directly in queries without vector indexes or embeddings, with performance benchmarks and operational caveats.

JevPostgreSQLSQL functions

0 likes · 5 min read

Semantic Filtering in Postgres Without Vector Indexes: pg-jev Hands-On

AI Engineering

Oct 2, 2026 · Artificial Intelligence

Karpathy: Replace Raw AI Text with Diagrams, Interactive Pages & Videos

Andrej Karpathy argues that AI now generates output faster than humans can comprehend, proposing four formats — simplified technical English, diagrams, interactive web pages, and explanatory videos — to make AI outputs verifiable, while warning that richer formats make quality control harder.

AI output formatsASD-STE100Karpathy

0 likes · 7 min read

Karpathy: Replace Raw AI Text with Diagrams, Interactive Pages & Videos

AI Engineering

Oct 1, 2026 · Artificial Intelligence

Gemini 4 Argon Matches GPT-6 Astra Benchmarks with Lowest Hallucination Rate

Google DeepMind's Gemini 4 Argon matches GPT-6 Astra on key benchmarks while achieving a 15% hallucination rate—the lowest among peers—with a 1M token output limit, aggressive introductory pricing, and a security-first rollout to network defenders.

AI benchmarksAgent CapabilitiesGPT-6 Astra

0 likes · 9 min read

Gemini 4 Argon Matches GPT-6 Astra Benchmarks with Lowest Hallucination Rate

AI Engineering

Sep 30, 2026 · Industry Insights

Trump Renames AI 'Super Intelligence' by Executive Order; Six Firms Sign Voluntary Safety Pact

The article analyzes Trump's executive order renaming AI to 'Super Intelligence' in federal communications without new regulations, and a same-day voluntary safety agreement signed by Google, Anthropic, Meta, OpenAI, xAI, and Nvidia that lacks enforcement mechanisms, highlighting the tension between symbolic terminology changes and self-regulatory pledges.

AI policyAI safetySuper Intelligence

0 likes · 11 min read

Trump Renames AI 'Super Intelligence' by Executive Order; Six Firms Sign Voluntary Safety Pact

AI Engineering

Sep 30, 2026 · Artificial Intelligence

GPT-6.1 Sol: Near-Astra Performance at One-Fifth the Cost

OpenAI's GPT-6.1 Sol delivers near-GPT-6 Astra performance on coding and computer-use benchmarks at one-fifth the cost, with improved factual accuracy and safety, available now for Plus, Pro, Business, Enterprise, and Edu users via ChatGPT Work, Codex, and API.

AI modelComputer UseGPT-6.1 Sol

0 likes · 4 min read

GPT-6.1 Sol: Near-Astra Performance at One-Fifth the Cost

AI Engineering

Sep 30, 2026 · Industry Insights

OpenAI DevDay 2026: The 5 Announcements That Reveal Their Agent Empire Strategy

OpenAI's 2026 DevDay unveiled Dots, a 24/7 personal agent platform; Decisions API for 10x faster classification; Agents API with computer control; Sign in with ChatGPT shifting inference costs to users; and Spaces for team collaboration — together signaling a full-stack agent ecosystem play.

AI AgentsAgents APIChatGPT Spaces

0 likes · 13 min read

OpenAI DevDay 2026: The 5 Announcements That Reveal Their Agent Empire Strategy

AI Engineering

Sep 26, 2026 · Industry Insights

Opus 5.5 Generates Full Videos with Code: Video Skills Become Obsolete

The author of the 10k-star video-shotcraft project demonstrates that Opus 5.5 eliminates the need for handcrafted video skills, as the model now handles coding, music synthesis, and pacing automatically, turning skills into optional creative guides rather than necessities.

AI video toolsGenerative AIOpus 5.5

0 likes · 3 min read

Opus 5.5 Generates Full Videos with Code: Video Skills Become Obsolete

AI Engineering

Sep 25, 2026 · Artificial Intelligence

Stop Claude Opus 5.5 Token Waste: 4 Configuration Steps

This article outlines four practical configuration steps to reduce token consumption when using Claude Opus 5.5: setting reasoning effort to medium, applying prompt audits, defining stop-and-ask rules in CLAUDE.md, and moving task lists out of conversation context into a separate TASKS.md file.

CLAUDE.mdClaude Opus 5.5TASKS.md

0 likes · 3 min read

Stop Claude Opus 5.5 Token Waste: 4 Configuration Steps

AI Engineering

Sep 24, 2026 · Artificial Intelligence

CLM-8B: System One Decision Model 9x Faster Than Jev

CLM-8B is a contrastive language model that maps states and actions to a shared vector space for fast decision-making, matching Jev's zero-shot performance on benchmarks like WikiRacing and Super Mario while being 9x faster, and serves as a verifier setting new SOTA on DeepSWE and Terminal-Bench with 4-5x speedup using decoupled encoders and vector caching.

CLM-8BContrastive LearningScaling Laws

0 likes · 6 min read

CLM-8B: System One Decision Model 9x Faster Than Jev