prompting
In-context learning Lesson
In-context learning is a language model's ability to pick up a new task from examples placed in its prompt, without any change to its weights, and it is the reason prompting works at all.
Chat templates: the invisible tags that tell a model who is speaking Lesson
A language model never sees a conversation - it sees one long string, and small marker tokens are the only thing telling it which parts are your instructions, which are its own thoughts, and which are untrusted data from the outside world.
DeepSeek's low effort setting writes more than its high setting, because the dial is just a prompt News
A reproduction across both a local copy and DeepSeek's hosted API found V4 Flash consuming substantially more tokens on its low reasoning-effort setting than on high, and the released encoder explains why: low injects no instruction at all while high prepends a paragraph demanding exhaustive deliberation.
Asking a model to check its own work lost every comparison against just sampling more answers News
A controlled experiment counting every token spent found that seven popular self-improvement methods - self-refinement, reflection, debate, best-of-N selection - never reliably beat the simplest baseline of generating several answers and taking the most common one, and ten of them were reliably worse.
Anthropic says it deleted over 80% of Claude Code's system prompt with no measurable loss News
Anthropic reports removing more than 80% of Claude Code's system prompt for its newest models without measurable degradation on internal coding evaluations, moving the deleted guidance into tool schemas, skills and memory instead.
Chain-of-thought: why making an AI think out loud makes it smarter Lesson
Asking a model to work through a problem step by step, instead of blurting an answer, dramatically improves it on hard tasks. Here is why that simple trick works, what it really buys the model, and where it backfires.