Theo on T3 Code: 10x More Merges Despite Modest Code Generation Gains

X postTheo - t3.ggOpinion

Theo (@theo) shares on X that T3 Code has impacted his personal productivity more than any prior tool or model.

Key points

  1. Theo notes that he generates around 20% more code with T3 Code.
  2. However, the volume of code he successfully merges has increased tenfold.
  3. The primary efficiency gain comes from shipping and integrating changes rather than raw code output.

Why it matters

Discussions surrounding AI-assisted coding frequently emphasize generation speed. Theo's experience indicates that tooling provides the highest leverage when it shrinks the gap between drafting code and merging it.

Analysis

Theo highlights a distinction between generative volume and practical delivery. A modest 20% increase in code written leading to 10x more merges suggests that the tool effectively eliminates friction in testing, refining, or context management.

Original post

Theo - t3.gg

@theo · 9 August 2026

T3 Code has affected my productivity more than any model or tool in my life. I'm generating like 20% more code, but I'm merging 10x more.

1.3k likes128 replies147 bookmarks94.7k views

View on X
More posts in the thread (3)
  1. @just_some_dev 🫡
  2. @bladearc4 Go to the session?
  3. @deckard_the_dev 🫡
Selected replies (5)
  • @hsprafrique @theo This hits different. I’ve been running multiple agents for months and still felt like I was drowning in threads, half-finished worktrees, and the constant “wait which one was doing what?” tax. T3 Code fixed that exact pain. The ability to spin something up, keep it cleanly
  • @JLarky @theo I fear not the man who has pushed slop PRs to 1000 projects, but I fear the man who has pushed 1000 slop PRs to one project
  • @deckard_the_dev @theo A Youtuber is outpacing products billion dollar companies make Crazy...
  • @novalinget @theo The bottleneck was never code generation. It was the distance between “finished” and “shipped.” Reducing that distance changes everything.
  • @blaqat_ag @Jony_David @theo this is why t.co/MqVYCOykM6

Links and tools from this entry

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • X post:Theo - t3.gg

    T3 Code: New Community Contributions and Feature Updates

    Theo (@theo) highlights that Matt Feroz has already landed two pull requests in T3 Code with more in the pipeline. A linked video by Matt reviews recent feature additions to the software.

    61bookmarks43.8kviews

    AI & LLMs· Announcement

  • X post:Theo - t3.gg

    Theo on the rollout of Astra and codebase use cases

    Theo (@theo) notes that Astra is rolling out and encourages developers to push the system on their codebases, starting with audits to clean up poor-quality code.

    7.6kbookmarks423.1kviews

    AI & LLMs· Opinion

  • X post:Mario Zechner

    Pragmatic Leverage in the AI Software Factory

    Mario Zechner highlights an analysis by Dex Horthy on achieving true leverage with AI in software engineering. Horthy argues that accelerating code generation alone yields minimal overall gains, as writing code historically represents only 25 to 50 percent of delivery time. Substantial acceleration occurs only when AI aids planning and alignment.

    913bookmarks98.2kviews

    AI & LLMs· Opinion

  • X post:Christian Bager Bach Houmann

    t3-pstack: Porting the pstack Agent Framework to T3 Code

    Christian Bager Bach Houmann has ported Lauren Tan's pstack framework to T3 Code. The tool directly integrates pstack with T3 Code's native MCP tooling, enabling multi-model reviews across Claude, GPT, and Grok.

    1.1kbookmarks42.1kviews

    AI & LLMs· Tool

  • X post:ClaudeDevs

    How the Claude Code Team Redesigned Code Review for AI

    Around 90 percent of Claude Code is written by Claude itself. The Anthropic engineering team shares how shifting to automated, multi-layered reviews more than doubled merged pull requests while cutting reverts by over 40 percent.

    10kbookmarks1.6mviews

    AI & LLMs· Opinion

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.