You have probably seen this with Claude Code or any long agent run: – it repeats work
– it forgets a decision
– it argues with stale instructions
– it misses the exact file you mentioned earlier
– the API bill keeps climbing That is not random.
CODE
-
Systematic failures in long agent runs: repetition, forgetting, high API bill
By
–
-
General-Purpose AI Agent Surpasses Karpathy’s Auto-Researcher by Self-Improvement
By
–
A GENERAL-PURPOSE AGENT SURPASSED KARPATHY'S AUTORESEARCHER It wasn't designed for research. It simply improved itself until it achieved it The framework behind it is called SIA by Hexo Labs and it's open source → The agent updates its own logic
→ Modifies its own weights -
Developers Using AI Agents for Large Pull Requests
By
–
Developers are using agents to write more "mega PRs."
-
Cursor Developer Habits Report on AI Coding
By
–
Introducing the Cursor Developer Habits Report.
— Cursor (@cursor_ai) 28 mai 2026
We’re sharing some of our findings on how software development is changing.
It’s based on the most comprehensive dataset on AI coding in the world, across all model families. pic.twitter.com/c4ZOeVErEOIntroducing the Cursor Developer Habits Report. We’re sharing some of our findings on how software development is changing. It’s based on the most comprehensive dataset on AI coding in the world, across all model families.
-
Five Emerging Themes in AI Research Report
By
–
Five themes emerged in our research: developer acceleration, the economics of intelligence, the power user gap, the rise of context, and the shift to automation. Read the full report here:
-
LangSmith Engine: AI Agent for Agent Optimization
By
–
join us for a behind the curtains look at LangSmith Engine (our agent that helps make your agent better)
-
Trend: Fewer Modes, More Autonomous AI Coding Agents
By
–
This is the AI coding agent trend in one sentence: Fewer modes. More autonomy. TRAE is moving from “pick the right coding assistant” to “tell one agent what to build and let it orchestrate the workflow.” Try it here:
-
SOLO Agent Dynamically Loading MCPs for Real-World Apps
By
–
The MCP side is especially interesting. TRAE’s unified SOLO Agent can dynamically load configured MCPs as the project evolves, instead of getting boxed into one rigid setup. That matters when you’re building real apps with databases, payments, AI services, and deployment tools.
-
Trae merges SOLO Builder and SOLO Coder into unified SOLO Agent
By
–
TRAE just killed the “which agent should I use?” problem. SOLO Builder and SOLO Coder are now merged into one unified SOLO Agent. One agent for frontend apps, complex programming tasks, routine dev work, MCPs, tools, and shipping. @Trae_ai
-
Rote: a local CLI for reproducible agent workflows
By
–
🚨 THIS IS EXACTLY HOW AI TOOLING SHOULD BE BUILT@Modiqoai just released Rote, completely dropping the bloated SaaS model.
— Charly Wargnier (@DataChaz) 28 mai 2026
It’s a FREE, local CLI that memorizes your agent's API sequences.
Imagine nailing a Jira flow once and handing that exact run to every dev on DAY 1 👀↓ https://t.co/DzI3DMhYdITHIS IS EXACTLY HOW AI TOOLING SHOULD BE BUILT @Modiqoai just released Rote, completely dropping the bloated SaaS model. It’s a FREE, local CLI that memorizes your agent's API sequences. Imagine nailing a Jira flow once and handing that exact run to every dev on DAY 1 ↓