Bookmarks

Playwright MCP server. Contribute to microsoft/playwright-mcp development by creating an account on GitHub.

Surprisingly (to me) Claude Code debugged my new ML-DSA implementation faster than I would have, finding the non-obvious low-level issue that was making Verify fail.

Go cryptography author Filippo Valsorda reports on some very positive results applying Claude Code to the challenge of implementing novel cryptography algorithms. After Claude was able to resolve a "fairly …

Today we’re releasing SWE-1.5, the latest in our family of models optimized for software engineering. It is a frontier-size model with hundreds of billions of parameters that achieves near-SOTA coding performance. It also sets a new standard for speed: we partnered with Cerebras to serve it at up to 950 tok/s – 6x faster than Haiku 4.5 and 13x faster than Sonnet 4.5. SWE-1.5 is now available in Windsurf!

Built to make you extraordinarily productive, Cursor is the best way to code with AI.

If you asked most people to name a defining feature of AI-generated writing, they’d probably say the em-dash — like this. Language models use em-dashes so much…

To really understand a concept, you have to "invent" it yourself in some capacity. Understanding doesn't come from passive content consumption. It is always self-built. It is an active, high-agency, …

One year from now, with the release of Chrome 154 in October 2026, we will change the default settings of Chrome to enable “Always Use Secu...

Tailscale Services is a new way to define available resources on your network and expand the granularity of your access controls to resources that may not have Tailscale installed on them.

If you have an AGENTS.md file, you can source it in your CLAUDE.md using @AGENTS.md to maintain a single source of truth.

I used to write more

Someone on Hacker News asked for tips on setting up a codebase to be more productive with AI coding tools. Here's my reply: Good automated tests which the coding agent …

One of the most controversial things I believe about good software design is that your code should be more flexible than your domain model. This is in direct…

When designing software systems, do the simplest thing that could possibly work. It’s surprising how far you can take this piece of advice. I genuinely think…

The big idea of James C. Scott’s Seeing Like A State can be expressed in three points: Modern organizations exert control by maximising “legibility”: by…

I have shipped a lot of different projects over the last ~10 years in tech. I often get tapped to lead new ones when it’s important to get it right, because I’m…

Reproducibility is a bedrock of scientific progress. However, it’s remarkably difficult to get reproducible results out of large language models. For example, you might observe that asking ChatGPT the same question multiple times provides different results. This by itself is not surprising, since getting a result from a language model involves “sampling”, a process that converts the language model’s output into a probability distribution and probabilistically selects a token. What might be more surprising is that even when we adjust the temperature down to 0This means that the LLM always chooses the highest probability token, which is called greedy sampling. (thus making the sampling theoretically deterministic), LLM APIs are still not deterministic in practice (see past discussions here, here, or here). Even when running inference on your own hardware with an OSS inference library like vLLM or SGLang, sampling still isn’t deterministic (see here or here).

hi, i'm jenn schiffer and this is my lifestyle blog

I gave a talk last night at Claude Code Anonymous in San Francisco, the unofficial meetup for coding agent enthusiasts. I decided to talk about a dichotomy I’ve been struggling …