Topic

AI Models & Tools

Coverage of the models and products people actually use: new releases from OpenAI, Anthropic, Google and the open-weight labs, plus the assistants, agents and developer tools built on top of them.

Each story explains what shipped, what changed from the previous version and who it is for, so you can decide whether a release is worth your time.

Showing 85–96 of 123 articles

RSS feed

Page 8 of 11

Claude Code
Claude Code Tips Boris Cherny Shared After Opus 4.7
Claude Code tips Boris Cherny shared after Opus 4.7: best practices, workflow improvements, and how to use Claude Code effectively.
Apr 17, 20267 min read
Foundation Models
Claude Opus 4.7 Autonomous Workflows: What Changed
Claude Opus 4.7 autonomous workflows explained: planning, persistence, guardrails, costs, and what actually changes in production AI pipelines.
Apr 17, 20269 min read
LLM Training
GFT reward fine-tuning paper: what the new method changes
A clear summary of the GFT reward fine-tuning paper, including unbiased group advantages, rectification, and LLM post-training impact.
Apr 17, 20268 min read
LLM Agents
Heartbeat-Driven Autonomous Thinking LLM Explained
Heartbeat-driven autonomous thinking LLM systems promise adaptive agent control. Here's what the paper means, when to use it, and when not to.
Apr 17, 20269 min read
LLM Memory
Knowledge graph persistent memory LLM guide with Tree-Sitter
Learn how a knowledge graph persistent memory LLM approach works with Tree-Sitter parser pipelines for better long-term context.
Apr 17, 20268 min read
AI Chatbots
Claude vs ChatGPT memory features: what actually matters
Claude vs ChatGPT memory features compared in depth, including long-term context, personalization, and why some users switch.
Apr 17, 20267 min read
OpenAI Business
OpenAI Business Users Strategy: Why the Enterprise Push Matters
OpenAI business users strategy signals a deeper enterprise push shaped by Anthropic, governance demands, and ROI pressure.
Apr 16, 20268 min read
LLMOps
Open source LLM pipeline with Groq and Snowflake
Build an open source LLM pipeline with Groq and Snowflake using retry logic, cost monitoring, governance, and production-grade patterns.
Apr 16, 20269 min read
Large Language Models
Numerical instability in large language models explained
Learn why numerical instability in large language models causes unreliable outputs, agent failures, and hard-to-debug behavior.
Apr 16, 20268 min read
Claude Troubleshooting
Claude code prompt cache workaround: fix stale caching issues
Use this Claude code prompt cache workaround to fix stale context, repeated outputs, and caching issues discussed on Hacker News.
Apr 13, 20268 min read
Multimodal AI
Claude vs ChatGPT Image Understanding: Safety and Accuracy
Claude vs ChatGPT image understanding matters for accessibility. See what this face analysis safety issue reveals about multimodal AI failures.
Apr 11, 20268 min read
Large Language Models
LLM post-training orchestration layer field guide
A practical guide to the LLM post-training orchestration layer, from verl workflows to eval gates, rollback, cost control, and scale.
Apr 10, 202610 min read

Claude Code Tips Boris Cherny Shared After Opus 4.7

Claude Opus 4.7 Autonomous Workflows: What Changed

GFT reward fine-tuning paper: what the new method changes

Heartbeat-Driven Autonomous Thinking LLM Explained

Knowledge graph persistent memory LLM guide with Tree-Sitter

Claude vs ChatGPT memory features: what actually matters

OpenAI Business Users Strategy: Why the Enterprise Push Matters

Open source LLM pipeline with Groq and Snowflake

Numerical instability in large language models explained

Claude code prompt cache workaround: fix stale caching issues

Claude vs ChatGPT Image Understanding: Safety and Accuracy

LLM post-training orchestration layer field guide