Kilo Blog
Subscribe
Sign in
Home
Guides
AI Models
Community
Company
Try Kilo
Archive
Latest
Top
Discussions
The Fastest Nemotron Yet: Embracing NVIDIA Nemotron 3.5 Lightning in Kilo
A customizable open model optimized for always-on agents
Aug 11
•
Ari Messer
7
Metabase Incident Impacting Kilo Code Data
August 9, 2026 14:50 UTC Update
Aug 7
Meta Will Cut Your Token Bill 20x. The Price Is Your Prompts.
Meta’s new coding agent ships with two prices for the same model, and the cheap one is paid for in your source code.
Aug 6
•
Arkadiy Kondrashov
6
1
How Many Spoons Does Your AI Coding Tool Cost?
Every broken environment and silent failure spends a team’s energy before it spends its time. Model lock-in just became the newest source of that tax.
Aug 6
•
Dawn Wages
5
1
Your Agent Has Too Much Context
Specs and instruction files feel like a safety net. But pile on too many and the agent gets confused rather than sharper. So what’s the actual source of…
Aug 5
•
Arkadiy Kondrashov
11
2
The Subtle Art of Tokenrelaxxing
Say goodbye to tokenmaxxing and hello to the calm of productivity
Aug 5
•
Ari Messer
9
Kilo Code’s JetBrains plugin was built for split mode from day one
A native Kotlin plugin split across frontend and backend modules, so the UI stays local while indexing and execution run wherever your code lives.
Aug 4
•
Arkadiy Kondrashov
6
1
Code Review Has Changed. The Contract Needs to Change Too.
For years, code review has been one of the core rituals of software engineering.
Aug 3
•
Emilie Schario
8
1
We analyzed 10,643 AI code reviews.
Open-weight models showed comparable findings at 16x lower cost per token.
Aug 3
•
Arkadiy Kondrashov
8
1
July 2026
Code Is Cheap. Review Is Expensive.
AI didn’t just speed up writing software. It inverted the economics of open source — and made review, not code, the scarce resource.
Jul 31
•
Arkadiy Kondrashov
11
Open Weights Is All You Need
Kilo’s perspective on the Open Weights AI letter.
Jul 31
•
Job Rietbergen
6
1
1
How AI Adoption Deepens in an Engineering Org
5 stages of feature usage, and what to measure at each one
Jul 30
•
Brian Turcotte
6
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts