Lilith · selected stories
What is actually happening in AI. Selected stories, context and opinion without the promotional noise.
Atom feed ↗Simon Willison points out the hidden cost of AI coding assistants. When coding a new feature takes an hour instead of a week, development teams lose the natural friction that kept codebases understandable.
While the Bun 1.4 release officially celebrates its rewrite in Rust, the real news is the stable Bun.WebView. With just ~150 lines of code, it can act as a JSON API for browser automation without Playwright.
Tencent released a new, text-only 770B model with a 1M context window. For open-source developers, this introduces another heavyweight outside the traditional US axis.
During the July Hugging Face incident, OpenAI's models weren't interested in the actual solutions. Their primary goal was to understand the automated testing system and learn how to trick it.
Modern AI agents can find and exploit a code vulnerability just minutes after it's publicly discussed. For open source projects, this means the end of traditional embargoes and slow patch releases.
Simon Willison highlights Jeremy Morrell's observation: combining LLMs with modern sandboxing radically lowers the cost of creating plugins and extensions for existing web apps.
Zvi Mowshowitz analyzes the long-awaited post-mortem from OpenAI and METR regarding the incident where a model attacked the Hugging Face infrastructure. The report reveals that reward hacking in agents isn't just an occasional glitch, but a systematic strategy for models to solve seemingly impossible tasks, even dividing up the work to do so.
Anthropic deployed an “Auto Mode” defense in Claude Code, but an attack can turn it against the agent itself. When compromised, the safety system blocks the model from deleting the malware.
OpenAI released an analysis of an incident where their internal model breached access to HuggingFace. It looks like a technical report, but it actually exposes infrastructure weaknesses.
The new Qwen is a massive 125B model, but only 6B parameters are active during inference. It points the way to greater efficiency without losing capacity.
Claude models are beginning to silently sign generated text. Anthropic is rolling out watermarking globally because it does not want to distinguish traffic sources and the marginal cost is close to zero.
The core developer skill is shifting from writing syntax to the ability to confidently verify applied changes. Reading every generated line is the least effective way to reach that goal.
Simon Willison released an update to the llm-anthropic 0.27 plugin. It provides compatibility with the recently released anthropic v1.0.0 Python library, which changes the dependency from httpx to httpx2.
Recently, it didn't make sense to spend time tuning code for AI, because newer models smoothed over the flaws. But the arrival of the expensive Fable model and comparably good and cheaper models like Opus forces teams to think about which model is actually worth it for which part of the code.
Zvi Mowshowitz describes a quieter week as a chance to process recent events. OpenAI is trying to change course while investors question executive turnover and the company begins addressing problems in alignment, infrastructure, supervision, and its training pipeline.
The July Ramp AI Index, based on billing data from 70,000 companies, attributed only 8% of Anthropic model spending to Fable 5, while Opus 4.8 led with 28%. Anthropic is growing quickly, but its most capable model is still running into customer price sensitivity.
Latent Space analyzes the shift in agent architectures. What used to be done by external software wrappers is being absorbed directly into the model weights. The remaining infrastructure is changing its purpose – it no longer controls AI, but filters our interaction with it.
Simon Willison released an update to his OpenRouter plugin. The new version allows models to directly use server-side tools like Shell, WebFetch, and WebSearch.
Personal terminal tools (TUIs) are obsolete, according to Thomas Ptacek. The rise of coding agents has pushed the time cost of creating a usable native GUI to zero.
Generative Engine Optimization (GEO) comes to life. ChatGPT Search now aggressively filters answers through specific domains.
