news

Tokenmaxxing is dead. It didn't produce the AI ROI companies wanted. - Fortune

Fortune's Jeremy Kahn argues the tokenmaxxing era ended nearly as fast as it began: Meta, Amazon, Microsoft, and Uber retired token-usage incentives once spend outran provable returns.

Published 2026-05-28Source: Fortune
Generated Tokenmaxxing editorial thumbnail for Tokenmaxxing is dead. It didn't produce the AI ROI companies wanted. - Fortune

Why it matters

The piece supplies the framework the obituaries lack: Azeem Azhar's productivity J-curve — returns dip before they climb because value requires redesigning workflows around the models, not maximizing consumption of them.

Tokenmaxxing read

Declaring usage metrics dead doesn't supply a replacement. The desk's read: cost-per-accepted-outcome is stage three of the J-curve, and most orgs killed their token leaderboards without building any measurement to replace them.

Source takeaway

Token leaderboards lasted weeks, but the durable claim is structural: real AI ROI appears only when firms rebuild processes and business models around the technology, and incumbents thinking too small leaves the opening for AI-native challengers.

Topic links

Related projects

Tools that match this angle

#1Direct
Routing

LiteLLM

BerriAI/litellm

An OpenAI-compatible gateway and SDK for calling many model providers with budgets, logging, load balancing, guardrails, and cost tracking.

50.2K8.8KSource-available
gatewaycost-trackingrouting
#2Direct
Observability

Langfuse

langfuse/langfuse

Open-source LLM engineering platform for observability, traces, metrics, evals, prompt management, datasets, and playground workflows.

29K3KSource-available
tracesevalscosts
#5Direct
Evaluation

promptfoo

promptfoo/promptfoo

A CLI and CI workflow for testing prompts, agents, and RAG systems across models, with evals and red-team style checks.

22.1K2KMIT
prompt-evalscirag
Related feed

More source-linked context

Generated Tokenmaxxing editorial thumbnail for “Tokenmaxxing is real, expensive & it’s spreading”: AI budgets are exploding - The New Stack
newsTN
newsmedium review

“Tokenmaxxing is real, expensive & it’s spreading”: AI budgets are exploding - The New Stack

AI accountability startup Lanai debuted Token Tuner, a beta that scores each employee's efficiency by matching token usage and model choice to task complexity — peers burned 10x the tokens for half the efficiency in one beta.

ai-spendcost-governanceexplainer
Read note
Generated Tokenmaxxing editorial thumbnail for Google touts its tokenmaxxing and capex spending amid AI orgy - The Register
newsTR
news

Google touts its tokenmaxxing and capex spending amid AI orgy - The Register

Google used token-throughput and capex numbers at I/O as a demand signal for Gemini, while openly acknowledging the 'tokenmaxxing' framing.

tokenmaxxingexplainerworkplace-ai
Read note
Generated Tokenmaxxing editorial thumbnail for Amazon employees admit to using AI unnecessarily to pump up internal usage scores — workers complain of intense pressure to use AI tools - Tom's Hardware
newsTH
news

Amazon employees admit to using AI unnecessarily to pump up internal usage scores — workers complain of intense pressure to use AI tools - Tom's Hardware

Amazon's internal AI usage targets can turn into tokenmaxxing: employees run unnecessary tasks in agent tools to climb dashboards rather than ship better work.

tokenmaxxingexplainerworkplace-ai
Read note