RESEARCH

Lilian Weng argues self-improving AI won't start with models rewriting their weights - it starts with the harness. Here's what that means for developers building agents.

A CS student built 30papers.com to make Ilya's legendary ML reading list more accessible. HN has thoughts on the source, the format, and why compression equals intelligence.

A new study from Dartmouth measures the impact of an AI tutoring platform on introductory statistics performance. Full engagement with the system correlated with significant exam score improvements, though selection bias remains a key limitation.

A controlled study of 660 Claude Code trials shows clean codebases reduce token usage by 7-8% and file revisitations by 34%, while pass rates stay the same. Traditional maintainability principles still matter in the age of AI coding.

A new SonarSource study finds clean code doesn't boost agent pass rates - but it cuts token usage by 8% and file revisitations by 34%. Here's what that means for your codebase.

The Program-as-Weights paper is a useful signal for developers: some LLM calls may move from per-request API prompts into compact local artifacts that behave like reusable fuzzy functions.

Anthropic's Claude Science combines scientific tools, local code execution, and HPC integration into one AI workbench. Here is how to access it, what it costs, and where it fits alongside Claude Code.

New research from MIT reveals that LLMs identify speakers by writing style, not by tags - meaning attackers who sound like the system effectively become the system. The findings explain why prompt injection remains unsolved.

The Multi-Stream LLMs paper argues that agents are bottlenecked by single chat streams. The practical takeaway is not to rebuild everything today, but to design agent runtimes around separated channels.

A trending refusal-direction paper is a reminder that model safety cannot be treated as a thin refusal layer. Builders need layered controls around the model.

Google's AI notebook that lets you ground a Gemini chat in your own uploaded sources. Generates summaries, mind maps, and podcast-style audio overviews.

2.5x faster Opus at a higher token cost (research preview).

Researcher, auditor, reviewer, and other ready-made subagent types.

Prevent bloating the main conversation with research or exploration.

A new study from nrehiew quantifies a problem every Claude Code, Cursor, and Codex user has felt: models making huge diffs for tiny fixes. Here is why it happens, why tests do not catch it, and what to do about it.

Set up Codex Chronicle on macOS, manage permissions, and understand privacy, security, and troubleshooting.