BKBen Kadishinengineering.fractional.ai00I wrote a profiling tool for agentsApr 9 · 2 min read · While building an agent for a client, we hit a scaling problem: a coordinator agent had 4-5 subagents each with 15-20 tool calls. Each tool result got appended to the context, then what started as a rJoin discussion
BKBen Kadishinengineering.fractional.ai00Tiny OCRFeb 11 · 3 min read · In our paper reading group last month I presented DeepSeek’s Context Optical Compression paper which claimed amazing performance with a much smaller model (3 billion parameters) than the previous fronJoin discussion
BKBen Kadishinengineering.fractional.ai00On the new larger context windowsNov 4, 2025 · 2 min read · Today the latest LLMs have large context windows up to ~1 million tokens. There are many occasions when this larger context window can be useful: Context engineering: injecting rich system/user conteJoin discussion
BKBen Kadishinengineering.fractional.ai00Let computers talk to computersApr 2, 2025 · 4 min read · Older computer systems required humans to adapt their behavior to computers. Instead of describing news articles you were interested in, to search a news index you might have to write Boolean keyword Join discussion
BKBen Kadishinengineering.fractional.ai00Using historical codebase to build an eval suiteNov 11, 2024 · 3 min read · Zapier has millions of users using thousands of integrations with different platforms. They’re constantly requesting new features they’d like to see, and Zapier has a team dedicated to identifying theJoin discussion
