1. **Analyze the Request:** * **Role:** News summarization expert. * **Task:** Summarize the provided article. * **Constraints:** * Concise (2-4 sentences). * Focus on the most important info. * No copy-pasting. * No restating the title (add new info). * Language: English. * **Input:** Title ("AI Has Amnesia. You're Paying. Blame the Architecture") and Source (HackerNews). *Wait, the "Article Text" section is empty except for the title repeated.* * **Problem:** The user provided the title but *no actual article text* to summarize. The "Article Text" block just repeats the title. 2. **Identify the Missing Information:** * I cannot summarize an article that isn't there. I can't generate a factual summary of a specific text if the text is missing. 3. **Formulate a Strategy:** * Since the prompt implies the user *thinks* they provided the text (or pasted a link/placeholder that didn't render), I need to inform them about the missing content. * However, looking at the prompt again: * Title: AI Has Amnesia. You're Paying. Blame the Architecture * Source: hackernews * Article Text: [Empty/Repeats Title] * *Self-Correction:* Is this a test of my external knowledge? The title refers to a specific concept in AI (LLMs) regarding context windows and high inference costs due to the Transformer architecture. This sounds like the article "The AI is Broken: It's Too Expensive" or similar discussions about the "Attention mechanism" and KV-Cache limits. * *Search/Knowledge Retrieval (Internal):
본문
In February 2024, Klarna announced what appeared to be a triumph of artificial intelligence at enterprise scale. Their AI assistant, built in partnership with OpenAI, had handled 2.3 million customer conversations in its first month — two-thirds of all service inquiries. Resolution times dropped from eleven minutes to two. The company projected forty million dollars in profit improvement. By mid-2025, that number had grown to sixty million, with the AI performing work equivalent to 853 full-time agents. The financial markets took notice; the efficiency narrative was compelling. Fifteen months later, Klarna's CEO Sebastian Siemiatkowski offered a different assessment. "We went too far," he admitted publicly. "Cost was a predominant evaluation factor, resulting in lower quality." Customers had reported what internal reviews confirmed: generic responses, repetitive answers, and an inability to handle nuanced problem-solving. The company began rehiring human agents. The Klarna reversal is instructive not because artificial intelligence failed, but because of how it failed. The system performed adequately on transactional queries — straightforward requests with predictable resolutions. It degraded on precisely the interactions that matter most: complex issues requiring accumulated context, customer history, and the kind of institutional memory that distinguishes service from processing. Klarna is not an outlier. It is an early signal of a structural limitation appearing across enterprise AI systems. Klarna's AI could retrieve similar responses. It could not precisely recall what it needed to know. This pattern has a name. I call it context decay: the systematic erosion of AI-generated institutional knowledge through architectural failure to precisely recall it. The Retrieval Tax To understand the scale of what enterprises are paying, consider the market trajectory. Enterprise spending on generative AI grew from $11.5 billion in 2024 to $37 billion in 2025 — a threefold increase in twelve months. Inference — the cost of actually running AI models — now accounts for 85 percent of enterprise AI budgets. Five hundred companies spend more than one million dollars annually on AI APIs alone, up from a dozen two years ago. Here is the paradox: per-token costs have dropped by a factor of one thousand. Yet total enterprise spending surged 320 percent. The efficiency gains are being consumed — by volume, by architectural overhead, and by waste that current systems make invisible. The source of that waste requires a brief explanation of how AI memory currently works. Large language models are stateless — when a session ends, they retain nothing. To give AI systems access to prior knowledge, the industry adopted retrieval-augmented generation, or RAG. When context is needed, the system queries a database and retrieves content that appears semantically similar to the current request. This retrieved content is then injected into the conversation as tokens — and billed accordingly. The limitation is structural. Similarity retrieval returns probabilistic approximations rather than deterministic recall. The architecture creates four distinct taxes. The re-retrieval tax When a session ends or a context window fills, the model discards everything it learned. To continue working, previously known context must be retrieved and re-injected. The enterprise pays to teach the AI something. Then pays again to retrieve it. Then pays again when the context clears and the cycle repeats. The same institutional knowledge, tokenized and billed multiple times — not because new value is being created, but because the architecture cannot retain what it already learned. The over-retrieval tax RAG architectures retrieve by similarity, not precision. To increase the likelihood of capturing relevant content, the system retrieves broadly — returning chunks of text that scored above a similarity threshold, regardless of whether they are specifically needed. Industry benchmarks illustrate the inefficiency: a system retrieves ten documents "to be safe," injecting 8,055 tokens into the context window to produce a 50-token answer. Hidden system prompts add another 500 to 3,000 tokens per request. Studies suggest that context pruning and retrieval optimization can reduce token consumption by 40 to 70 percent — which implies that 40 to 70 percent of current spending retrieves context the AI does not need. $10–20 billion Estimated annual waste from architectural inefficiency, based on $37B enterprise AI spending with 85% on inference and 40-70% over-retrieval. The labor tax Beyond the invoice, there is the cost measured in human attention. Every developer who re-explains project context to a coding agent that should already know it. Every analyst who re-states prior conclusions because the AI cannot recall them. Every employee who spends the first minutes of an AI interaction rebuilding context that existed in a previous session. The industry has developed wor