Coffee With Developers
•
Aug 17, 2026
Why Token Reduction Isn’t Cost Reduction - Dave Anderson & Sarel Weinberger, PhD.
Dave Anderson, Sarel Weinberger, Phd
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
Compressing LLM inputs doesn't save money. It forces models to work harder, driving up compute costs by 50%. Learn smarter resource allocation techniques that actually lower your bills.
Starting at 8:29 · Watch from the beginning
Checking access…
Playback and chapters load privately for Free videos.
Matching moments
More from Coffee With Developers
Upcoming sessions on this topic
Starts in 5 days
Conference India 2026
November 25–26, 2026
Bengaluru, India
-
Stop Counting Tokens, Start Making Them Count
Vicky Israni · GitHub
Thu 26 Nov · Stage 1 - powered by IBM
-
Your AI Agents Are Bleeding Tokens: Building a Runtime Cost Control Plane for LLMs

Aakriti Aggarwal & Bhavishya Pandit
Wed 25 Nov · Stage 1 - powered by IBM
-
AI Is the Easy Part: Why Faster Engineers Don't Make Faster Businesses
Bharat Sharma · Booking
Wed 25 Nov · Mainstage
Related videos
Related articles
DC
Daniel Cranney
DC
Daniel Cranney
ME
Markus Eisele
DC
Daniel Cranney
From learning to earning
Jobs that call for the skills explored in this talk.
9 days ago
Senior Data Scientist - AI Tooling
Intercom
Dublin, CA, United States
Expert
Remote
Airflow
Standard Sql
Salesforce.Com
25 days ago
Applied AI Health Data System Engineer-Senior Manager
PwC
Kansas City, MO, United States
Expert
$124k–280k
Git
Keras
NoSQL
7 days ago
Senior AI Scientist - Model Training & Architecture
BWI GmbH
Hamburg, Germany
Expert
€87k–113k
NoSQL
QLoRA
Docker
9 days ago
AI Scientist - Model Training & Architecture
BWI GmbH
Bamberg, Germany
Expert
€87k–113k
NoSQL
QLoRA
Docker
5 days ago
Lead Engineer, Google Cloud
PwC
Atlanta, GA, United States
Expert
$99k–232k
LangChain
Google Cloud
Generative AI
10 days ago
Principal Software Engineer, Copilot Code Review
GitHub
Beverly Hills, CA, United States
Expert
Remote
Ruby
Golang
Github