How did we go from opening Stack Overflow to solve one bug, to agents writing entire features on their own? That didn’t happen overnight, but in slow progress in about 5 years. And today, I want to walk you through the full story. The timeline, the tools, the tweets, the
AGENTS
-
Training Agents with Failures as Optimization Signal
By
–
The trick in our case is treating failures as training signal, which only works with a reliable verifier and a held-out gate. Open-ended agent work without success metrics is the hardest case to optimize this way.
-
Multi-Turn Agent Evaluation and Context Compaction Limits
By
–
Paper does test multi-turn (24 tool calls in OfficeQA, 30 turns in SpreadsheetBench, 50 steps in ALFWorld), but mid-session auto-compaction isn't part of the eval. Skill being under 2K tokens probably helps it survive compaction, but not validated against that failure mode.
-
AI turns past prompts into reusable skills and subagents
By
–
It will look through your past sessions and turn repeated prompts into reusable skills + subagents
-
Turn Claude into Specialist Marketing & Business Agents
By
–
If you find this useful, also check this out. Turn Claude into 20+ different specialists for marketing & business. Install real expertise, not just prompts. Get my Claude skills bundle
-
Automated 30-day review of recent AI work using memory and git
By
–
The text version of the prompt: "Look back over my recent work from the last 30 days using all available context. Use available evidence in this order:
– Session Memory summaries and MEMORY. md entries
– Git log and recent commit history across branches
– CLAUDE. md and -
Engineer Uses Claude Code Agent to Audit and Delete Unused Redis Instances
By
–
An Anthropic engineer pointed Claude Code at his old startup's infrastructure and told it to find ways to save money. It audited the full stack, identified 3 unused Redis instances he'd been paying for, proposed deleting them, and after he approved each step, executed the
-
Types of LLMs in AI Agents by @ingliguori
By
–
Types of #LLMs in #AIAgents by @ingliguori #GenerativeAI #ArtificialIntelligence #MachineLearning #ML
-
EVE-Agent forces verifiable source spans for AI learning
By
–
Can your AI justify what it learns, or is it just guessing? Researchers from Fujitsu and the University of Tokyo present EVE-Agent: a self-evolving system that forces every training example to include a verifiable source span — no more learning from unsupported answers.
-
Agentic Tools for Automated Test Case Writing
By
–
Depends on the job. Quick checks, curl still wins. Real suites, an agentic tool that writes and maintains the cases.