Themata.AI
Themata.AI

Popular tags:

Developer toolsAI agentsDiscussionTrendingLLMsAI ethicsClaudeCode generationAI safetyOpenAI

AI is changing the world. Don't stay behind. Clear summaries, community insight, delivered without the noise. Subscribe to never miss a beat.

© 2026 Themata.AI • All Rights Reserved

Archive

|

Topics

|

Privacy

|

Cookies

|

Contact
AI agentsDeveloper toolsCopilotLLMs

Billing can be bypassed using a combo of subagents with an agent definition

Billing can be bypassed using a combination of subagents with an agent definition, resulting in unlimited free premium requests. · Issue #292452 · microsoft/vscode

github.com

February 8, 2026

4 min read

🔥🔥🔥🔥🔥

58/100

Summary

Billing can be bypassed in Copilot by utilizing subagents and tool calls that do not consume requests, along with free models like GPT-5-mini and GPT-4.1. Defining an agent for a subagent and specifying a model for that agent enables unlimited free premium requests.

Key Takeaways

  • Users can bypass billing for premium requests in Copilot by utilizing subagents and tool calls that do not incur request costs.
  • By starting a chat with a free model like GPT-5 Mini and creating a subagent with a premium model, users can access premium features without additional charges.
  • A custom script can be developed to repeatedly invoke premium models, allowing for extensive use without exceeding the initial request cost.
  • The system lacks API validation for message types, which may enable further exploitation of the billing system.
Read original article

Coverage & discussions

Hacker News · github.com

Billing can be bypassed using a combo of subagents with an agent definition ↗

Community discussions

Hacker News discussion ↗

Historical count: 5 · 5 saved in sample · Historical sample

Analysis ready

Community Sentiment

Negative

Concerns

  • The reliance on vague instructions to control LLMs raises concerns about repeating past mistakes in AI safety and control mechanisms.
  • The increasing presence of individuals impersonating maintainers in AI projects highlights a growing trust issue in community contributions.
  • The perception that Microsoft is not putting in sufficient effort on AI projects suggests a decline in innovation and reliability.

Related Articles

GitHub - IsuruMaduranga/harness-engineering-101: Harness Engineering 101 — building AI agents from first principles. The LLM is the brain; the harness is the body.

Harness Engineering 101: The LLM is the brain, the harness is the body

Oct 19, 2026

If you don't run your own LLM proxy, how the fuck do you even know whats going on?

If you don't run your own LLM proxy, how do you know whats going on?

Oct 18, 2026

Hybrid Reasoning Agents

Hybrid Reasoning Agents: LLM agents that think in latent space, act through text

Oct 18, 2026

How to make System 1 LLMs show System 2 competencies?

How to make System 1 LLMs show System 2 competencies?

Oct 16, 2026

My old job feels very distant now

My old job feels distant now

Oct 16, 2026