·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
OpenAI is finally merging ChatGPT’s chat and Work tabs59m◆Stop counting tokens, start counting what ships1h◆The agentic web is here5h◆Enhancing Sentiment Classification on Small Datasets through Data Augmentation and Transfer Learning9h◆DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving9h◆CodeLift: Your Test Suite Is Secretly a Dense SWE Curriculum9h◆Cumulative Marginal Matching for One-Step Diffusion9h◆Thinking Inertia: LLMs Keep Thinking When Told Not To9h◆Beyond Public Access in LLM Pre-Training Data9h◆M$^\star$: Every Task Deserves Its Own Memory Harness9h◆On k-nearest-neighbor regression in metric spaces9h◆CausalGrade: Evidence-Guided Causal Graph Scoring with Jev9h◆Leveraging Quantum Measurement Randomness for Shot-Efficient Diffusion Models9h◆Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network9h◆Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance9h◆On the Generation Order in GFlowNets9h◆Differential rank preservation manifold learning9h◆Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News9h◆Comparative Evaluation of LLM-Based Review Paradigms for Academic Paper Quality Assessment9h◆BlindToChange: AI Agents Can Find Changes When Asked But Do They Look When Needed?9h◆OpenAI is finally merging ChatGPT’s chat and Work tabs59m◆Stop counting tokens, start counting what ships1h◆The agentic web is here5h◆Enhancing Sentiment Classification on Small Datasets through Data Augmentation and Transfer Learning9h◆DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving9h◆CodeLift: Your Test Suite Is Secretly a Dense SWE Curriculum9h◆Cumulative Marginal Matching for One-Step Diffusion9h◆Thinking Inertia: LLMs Keep Thinking When Told Not To9h◆Beyond Public Access in LLM Pre-Training Data9h◆M$^\star$: Every Task Deserves Its Own Memory Harness9h◆On k-nearest-neighbor regression in metric spaces9h◆CausalGrade: Evidence-Guided Causal Graph Scoring with Jev9h◆Leveraging Quantum Measurement Randomness for Shot-Efficient Diffusion Models9h◆Repair Brain Damage: Real-Numbered Error Correction Code for Neural Network9h◆Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance9h◆On the Generation Order in GFlowNets9h◆Differential rank preservation manifold learning9h◆Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News9h◆Comparative Evaluation of LLM-Based Review Paradigms for Academic Paper Quality Assessment9h◆BlindToChange: AI Agents Can Find Changes When Asked But Do They Look When Needed?9h◆
News/Stop counting tokens, start counting what ships
mit-tech-review
PublishedNovember 2, 2026 at 1:10 PM

Stop counting tokens, start counting what ships

Stop counting tokens, start counting what ships
Source
technologyreview.comfull article ↗
Read on mit-tech-review→
Publisher summary· verbatim

When a developer gives an AI agent a coding task, the agent does more than answer once. It plans, generates code, runs tests, and repeats the process to correct errors. A single task can use 10 to 50 times more tokens than a basic chat prompt. The more useful the agent becomes, the more calls it mak

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Source
↗
mit-tech-review
Read original ↗All from mit-tech-review →

No replies yet. Be first.

Source
↗
mit-tech-review
Read original ↗All from mit-tech-review →

Related coverage

More from MIT-TECH-REVIEW
mit-tech-reviewThe agentic web is here5h
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on mit-tech-review ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews