Composer: Building a fast frontier model with RL
Cursor Team · Cursor
Cursor says Composer achieves frontier coding results with generation speed four times faster than similar models.
Open library
The library
The essential reading of generative AI and agents, open in a clean reading view, with Meow and Standard summaries when available. No account needed to read.
560 papers · 558 with a Meow summary · 333 posts
The selected papers and blogs: the essential papers of generative AI and agents, and the key lab publications and essays, each with Meow and Standard summaries.
AutoGen: Enabling next-generation large language model applications
Alyssa Hughes · Microsoft Research
AutoGen makes multi-agent conversation the organizing layer for complex LLM workflows, with humans and tools able to join.
Four AI Agent Strategies That Improve GPT-4 and GPT-3.5 Performance
Analytics DeepLearning.AI · Andrew Ng
Agent workflows can improve performance by letting a model revise its work, not just by upgrading to a newer model.
The Rise of the AI Engineer
Latent.Space · Latent Space
The author argues that foundation-model APIs and open-source models are shifting AI work toward engineers who turn models into products, not only researchers who train them.
How Claude Code is used in practice
Anthropic
Anthropic’s evidence suggests Claude Code shifts implementation work outward: users steer the goal, while task-specific expertise remains linked to success.
How Cursor Router chooses the right model for the task
Connor O’Keefe · Cursor
Cursor bases routing on production developer work, not benchmark scores.
Agent swarms and the new model economics
Wilson Lin · Cursor
The authors argue that agent swarms work better when task decomposition, shared context and coordination are engineered—not when agents simply commit faster.
Governing agent autonomy with Auto-review
David Gomes · Cursor
Auto-review treats agent permission as a risk dial: it judges a proposed action in context instead of applying one global allow-or-stop rule.
What we’ve learned building cloud agents
Josh Ma · Cursor
Cloud agents need an operating layer around the model—not just a local agent copied onto a server.
Continually improving our agent harness
Stefan Heule · Cursor
Cursor argues that an agent’s harness—not just its model—needs continuous tuning, measurement, and repair; that orchestration will matter even more as agents begin delegating work.
Scaling long-running autonomous coding
Wilson Lin · Cursor
Cursor’s experiments suggest long-running autonomous coding scales through deliberate coordination, not agent count alone.
We're going to need default hard budget caps on pretty much everything
Simon Willison
Willison argues that usage-based services should stop spending at a hard monthly cap by default, because warning-only limits leave users exposed to runaway costs from agent-launched code.
Vibe coding and agentic engineering are getting closer than I’d like
Simon Willison
Willison says vibe coding and agentic engineering are converging: AI lets him take on more, but less code review makes trust and responsibility harder.
Devin Fusion
Cognition
Cognition argues that cheaper coding models can cut costs without sacrificing frontier-level intelligence: Devin Fusion keeps a frontier agent in the loop and delegates suitable work to a sidekick.
What We Learned Building Cloud Agents
The Cognition Team · Cognition
Cognition's central warning: a cloud agent needs isolated, resumable compute and an organization prepared to operate it—not merely a CLI inside a container.
Multi-Agents: What's Actually Working
Walden Yan · Cognition
On Devin-written PRs, Devin Review catches an average of 2 bugs per PR; roughly 58% are severe.
Claude Code and What Comes Next
Ethan Mollick
Claude Code’s leap comes from pairing stronger autonomous work with an “agentic harness” that manages tools, memory, and specialized tasks—enabling long projects, but not removing the risks of computer access.
Harness, Scaffold, and the AI Agent Terms Worth Getting Right
Sergio Paniego · Hugging Face
A useful agent glossary separates scaffolding (what the model works from) from the harness (what runs the model-and-tool loop), while warning that frameworks use the terms differently.
Terminally online Mistral Vibe.
Mistral
Mistral Vibe 2.0 adds controls to a terminal-native coding agent: users can delegate targeted tasks and get clarification options when intent is ambiguous.
Get Good at Agents
Nathan Lambert
Lambert argues that capable agents shift work from doing each task yourself to choosing, directing, and coordinating what gets done.
Claude Code Hits Different
Nathan Lambert
The author argues that Claude Code with Opus 4.5 makes software building more accessible, and that the product experience—not just the model—helps drive the change.
Using Local Coding Agents
Sebastian Raschka, PhD · Sebastian Raschka
A local coding agent is more than a model: its runtime, harness, permissions, and task-specific evaluation determine whether it is useful and safe.
Components of A Coding Agent
Sebastian Raschka, PhD · Sebastian Raschka
A coding agent’s advantage is not just the model: a harness wraps it in a control loop that gathers repository context, uses tools, and manages state and execution.
The Evolution of the Agent Harness
Dan McAteer · Latent Space
McAteer argues that agent gains come from model–harness co-evolution: models absorb capabilities once supplied by scaffolding, shifting the remaining harness toward human attention.
How to Kill the Code Review
Ankit Jain · Latent Space
Jain argues that AI-scale development makes line-by-line human review untenable: people should approve intent and constraints, while layered checks verify generated code.
DeepSeek Harness: Agentic Development Environment
DeepSeek
DeepSeek Harness is an open-source agent environment in worldwide public preview, built to grow through composable plugins.
How to Work and Compound with AI
Eugene Yan
Yan argues that AI work compounds when artifacts become reusable context and corrections improve future sessions. Reliable scaling depends on good context, explicit checks, and a feedback loop.
When AI writes almost all code, what happens to software engineering?
Gergely Orosz · The Pragmatic Engineer
AI coding has crossed a practical threshold for some engineers, but the author argues that faster code shifts value toward specifying, testing, and owning software—not away from engineering.
My AI Adoption Journey
Mitchell Hashimoto
The author found coding-agent value by changing the workflow, not by asking a chatbot harder: learn task boundaries, delegate likely wins, and build checks that catch mistakes.
AGENTS.md outperforms skills in our agent evals
Vercel
Vercel’s evals favor persistent, version-matched framework context over documentation an agent must remember to fetch.