Token saving in agent systems is often framed as an efficiency concern. A better framing is signal-to-noise control: every unnecessary token competes for attention, increases inference cost, and makes the next decision less precise. Current work on context compression, KV-cache compression, and long-running interactions points in the same direction.
The intuition that feeding a language model more information improves its outputs is wrong often enough to matter. Here is why, and what to do about it.
AI detectors can flag human writing, including historical and highly formulaic prose. Evidence exists for a false-positive risk affecting some non-native English writers; claims about autistic or physics-trained writers need direct validation. The detector score is not authorship evidence.
In early 2026, variants of a prompt about a nearby car wash spread online after some assistants recommended walking instead of taking the car. This is neither the tokenisation failure from the strawberry post nor the grounding failure from the rainy-day post. It is a pragmatic inference failure: the response followed the travel wording but missed the likely purpose of the trip, assigning its advice to the wrong interpretation of the question. A third and more subtle failure mode, with Grice as the theoretical handle.
A viral video this month showed an AI assistant confidently answering “should I go to the car wash today?” without knowing it was raining outside. The internet found it funny. The failure mode is real but distinct from the strawberry counting problem — this is not a representation issue, it is a missing-context issue. The words posed no special tokenisation difficulty. What the system lacked was access to the state of the world the question was about.
In late 2025, agentic coding tools went from impressive demos to daily infrastructure. The problem nobody talked about enough: when an LLM agent has write access to a codebase and no formal constraints, reproducibility breaks down. The Ralph Loop is a story-driven harness intended to bound that variability through one model invocation per attempt, scoped writes, and atomic state. These constraints make runs easier to inspect; they do not make an unpinned model deterministic.
Everyone has a Downloads folder full of “scan0023.pdf” and “document(3)-final-FINAL.pdf”. Renaming them by content sounds trivial — read the file, understand what it is, give it a name. The implementation reveals something useful about how LLMs actually handle text: what a token is, why context windows matter in practice, why you want structured output instead of prose, and why heuristics should go first. The repository is at github.com/sebastianspicker/AI-PDF-Renamer.
On 2 December 2024 I gave three workshops at HfMT Köln’s Thementag on AI and music education. The handouts covered data protection, AI tools for students, and AI in teaching. This post is the argument behind them — focused on the curriculum question that none of the tools answer on their own: what should change, and what should not?
The viral “three Rs in strawberry” test exposes a real mismatch between token-level input and character-level operations. It does not, by itself, identify one tokenizer boundary or explain any particular model response.