Pithy Cyborg | AI News Made Simple
Pithy Cyborg | AI News Made Simple
Building with AI is exciting right up until the tooling starts breaking in strange ways. In this category, I write about AI coding assistants, APIs, FastAPI streaming, async failures, malformed JSON, function calling, SDK weirdness, production integration problems, and the real engineering friction behind AI-powered software.
This category is for developers who want practical answers, not glossy demos. I focus on the bugs, edge cases, and system behavior that show up when you actually try to build reliable AI products.
Browse the articles below to explore AI coding and APIs in practice.
An AI coding assistant does not remember that it fixed a bug. Each new request sees the current state of the code and the current conversation context. If the fix was applied to one file but the bug's …
Continue Reading about Why Does My AI Coding Assistant Keep Reintroducing the Bug It Just Fixed? →
Yes. A retry wrapper on a non-idempotent tool call retries an operation that may have already succeeded. The model called the tool, the tool executed, the response was lost due to a timeout or network …
Continue Reading about Can a Retry Wrapper Make LLM Tool Calls Less Reliable Instead of More? →
Streaming sends tokens as they are generated rather than waiting for the complete response. When the complete response is valid JSON, streaming appears to work. The problem appears at the consumer: …
Continue Reading about Why Does Streaming JSON From an LLM Break Even When the Output Looks Valid? →
