News
Claude Fable 5 vs GPT-5. 5: better planning, similar execution
1+ week, 4+ day ago (131+ words) Update: We wrote this post on June 11 and published it on June 13. Would be interesting if you could run the same plan that got written with fable, but with cheaper models like glm5. 1 (5. 2 soon), m3 and k2. 6. gpt5. 5 still is extremely expensive, and somehow…...
Kilo Bench - Because Your Benchmark Score Doesn't Pay the Bill
2+ week, 2+ day ago (1025+ words) This is the problem Kilo Bench exists to solve. Open AI's response was to stop reporting SWE-bench Verified scores entirely. The problem isn't just contamination. It's scaffold inflation. The choice of agent orchestration layer " how it decomposes problems, which tools…...
We Asked Grok Build 0. 1 to Plan and Build a Webhook Service
3+ week, 6+ day ago (1094+ words) x AI released Grok Build 0. 1 as a new coding model priced at $1 per 1 M input tokens and $2 per 1 M output tokens with a 256 K context window. We ran it through Kilo Code (the VS Code extension) on a real backend…...
Running Google Ads from the terminal with custom AI skills
1+ mon, 2+ week ago (1496+ words) This is a writeup of what I built, how it's structured, and how I actually use it. Kilo CLI lets me pick a different model per task. That's the whole thing. I'm not stuck paying Opus prices to rename an…...
Claude Code Source Leak: A Timeline
2+ mon, 3+ week ago (1213+ words) How it happened: A debugging file called a source map (. map) was accidentally included in an update to Claude Code's public package (version 2. 1. 88). Source maps let developers translate compressed production code back into readable source. This one pointed to an…...
The Year Senior Engineers Stopped Rolling Their Eyes at AI Coding
5+ mon, 3+ week ago (1491+ words) As 2025 ends, something remarkable has happened. The same senior engineers who dismissed AI coding tools as "fancy autocomplete" in early 2025 are now shipping production code they've never read'and bragging about it. At the stroke of midnight in San Francisco, it's…...
This Week in Kilo Code: GPT-5. 1, Provider Upgrades, and CLI Improvements
7+ mon, 6+ day ago (309+ words) Welcome back to the weekly product roundup! This week brings full support for Open AI's newly released GPT-5. 1 model family, along with some ease-of-life fixes for the CLI, and several provider-level enhancements inside the extension. Open AI has released four…...
Gemini 3 Pro Preview is Now Supported in Kilo Code
7+ mon, 6+ day ago (484+ words) Google has just released Gemini 3, their most advanced model yet, bringing state-of-the-art reasoning, richer multimodal understanding, and dramatically more capable agentic behavior. Gemini 3 Pro Preview is available today across the entire Kilo Code ecosystem. You can use it through: The…...