software by Stafford Williams
blog more
- 2025-06-04 AI Code Assistance: Are we talking about the same thing?
- 2025-03-16 Embrace Vibe Coding, Know Its Limits
- 2025-03-09 You Might Not Need an AI Framework
- 2025-03-03 Understanding AI-assisted Coding Workflows
- 2025-01-29 Running DeepSeek R1 Locally
- 2025-01-12 LLM Agent Assisted Coding
- 2024-10-14 Comparing Netlify and Azure Static Web Apps
links more
If you had to access RavenDb 3.5 over REST API and were pondering how to so using a supplied api key and oauth, then this page is very helpful indeed.
Effective context engineering for AI agents
good context engineering means finding the smallest possible set of high-signal tokens that maximize the likelihood of some desired outcome
Anthropic releases Claude Sonnet 4.5 claiming it’s
the best coding model in the world.
API price remains the same as earlier versions at
$3/$15 per million tokens.
Also, ccusage deprecates blocks --live as the official way to track claude usage is via claude.ai/settings/usage.
Every team is at a different stage of collaboration and so it’s difficult to find a team charter template that fits all teams - I like this atlassian one even if just for the Team Preferences and Communication Channels sections.
Microsoft announces auto-model selection for VS Code that prioritizes Claude Sonnet 4 over GPT-5 for paid users
Use ccusage to track your live, daily, and monthly claude code token and dollar usage. In the case of subscription plans it shows you how much you would have paid were you using API. Also estimates your current block usage which you can use to predict whether you’re going to get rate limited at any given time.
Claude code supports remote MCP servers.
csharp
claude mcp add --transport http github https://api.githubcopilot.com/mcp/ \
--header "Authorization: Bearer <GITHUB_PAT>"
How we built our multi-agent research system speaks to Anthropic’s multi-agent build experiences.
We found that a multi-agent system with Claude Opus 4 as the lead agent and Claude Sonnet 4 subagents outperformed single-agent Claude Opus 4 by 90.2% on our internal research eval
However these architectures burn through tokens fast:
In our data, agents typically use about 4× more tokens than chat interactions, and multi-agent systems use about 15× more tokens than chats.
Cognition goes further in Don’t Build Multi-Agents
In some cases, libraries such as swarm by OpenAI and autogen by Microsoft actively push concepts which I believe to be the wrong way of building agents.
a tool that you can use to create and run Linux containers as lightweight virtual machines on your Mac. It’s written in Swift, and optimized for Apple silicon.
After installing and starting the service via container system start the cli gives you a similar experience to docker. Unfortunately in my case after resolving dated sources and switching dependencies to arm64 I discovered my Dockerfile candidate still had an x86 binary so I’ll need to find another candidate to test any performance improvements.
devlog more
- 2024-05-29 [spacetraders-v2] v2.14 - more data browser
- 2024-05-16 [spacetraders-v2] v2.13 - data browser
- 2024-05-04 [spacetraders-v2] v2.12 - reset 2024-04-09
- 2024-04-21 [spacetraders-v2] v2.11 - monitoring markets
- 2024-04-18 [spacetraders-v2] v2.10 - trading contracts
- 2024-03-31 [spacetraders-v2] v2.9 - improved waypoint monitoring
- 2024-03-28 [spacetraders-v2] v2.8 - over supply
notes more
- 2025-03-29 [ssl] mac keychain
- 2025-03-03 [javascript, timezones, vitest] timezones
- 2025-01-14 [bookmarklet, chrome] add text to clipboard
- 2024-12-11 [javascript, timezones] datetime libraries
- 2024-03-13 [azure-b2c] limits
- 2024-03-11 [azure-b2c] phone mfa - microsoft samples
- 2024-03-06 [http] testing