swift @gaoscode

https://t.co/0FbHmVhIS9 github.com/GaosCode Joined November 2025

Tweets

28
Followers

77
Following

123
Likes

1K

swift @gaoscode

a week ago

@thsottiaux A plan page like this.

0 0 0 14 0

View Details

@blueemi99 plan mode could be more systematic. for example, make it an independent feature with its own page, and organize plans as a DAG there instead of putting everything behind a slash command. feels like a better direction.

0 0 2 321 0

View Details

swift @gaoscode

3 months ago

@thorstenball Maybe plan mode just needs an upgrade like this.

0 0 3 49 0

View Details

swift @gaoscode

3 months ago

@tylerangert lmao, this is exactly what i'm building with PlanWeave: github.com/GaosCode/PlanW…

0 0 0 9 0

View Details

swift @gaoscode

3 months ago

@sydneyrunkle a stateful graph for coordinating agents' work, with dependencies, parallel execution, validation, feedback, and progress saved along the way github.com/GaosCode/PlanW…

0 0 0 8 0

View Details

swift @gaoscode

3 months ago

@ThePrimeagen apparently planweave. try to keep up. github.com/GaosCode/PlanW…

0 0 0 8 0

View Details

swift @gaoscode

3 months ago

@IntuitMachine Pretty close to PlanWeave. Every task sets its own anchor up front. Reviewer checks the result against it. Coordinator kills the graph on failure. github.com/GaosCode/PlanW…

0 0 2 311 1

View Details

swift @gaoscode

3 months ago

@sydneyrunkle A static graph sets the direction before execution. When an agent starts a specific task, it generates a smaller dynamic graph to guide the work. PlanWeave keeps the outer graph persistent while agents create local graphs inside it as they work. github.com/GaosCode/PlanW…

0 0 2 84 4

View Details

swift @gaoscode

3 months ago

@Saboo_Shubham_ That's pretty much where planweave is headed. The graph already drives execution and review. The next step is letting it restructure itself on the fly. github.com/GaosCode/PlanW…

0 0 3 365 5

View Details

swift @gaoscode

3 months ago

@steipete seems like you're looking for this DAG: github.com/GaosCode/PlanW…

1 1 9 4K 22

View Details

swift @gaoscode

3 months ago

@pashmerepat Agree with linus. AI is here to stay. When ai falls short at a task, we dig in and make it better. Each limitation is a challenge and an opportunity for engineers. No single limitation defines what ai can do.

0 1 2 261 0

View Details

swift @gaoscode

3 months ago

I think the key is to review the atomic plan before execution, and make sure you understand each step along with its expected outcome. This way you keep control from the high-level design all the way down to individual tasks. Code review can then be reserved for the cases where the plan (or test evidence) actually shows a specific problem.

0 0 1 739 0

View Details

antirez @antirez

3 months ago

It is my belief that many devs right now are not maximizing what they can do with automatic programming because they still look at the code. Doing it makes you the bottleneck. Your time is better invested in new ideas, QA, design, and asking yourself what is your goal.

271 255 3K 506K 880

View Details

swift @gaoscode

3 months ago

I miss Steve Jobs again. He understood that great products shouldn't create unnecessary choices. Now codex has a vague new Work mode. What is it actually for? It feels like openai copied another product's structure without asking whether codex was simply better without it.

0 1 3 253 1

View Details

swift @gaoscode

3 months ago

@theo absolutely

0 0 1 9 0

View Details

swift @gaoscode

3 months ago

@thsottiaux wait and see 👀

0 0 1 145 0

View Details

swift @gaoscode

3 months ago

This is basically externalized CoT for agent execution. strong models plan / coordinate / review, cheaper models execute. The key is moving the reasoning structure out of chat context and into durable execution state: task graph, prompt blocks, review gates, feedback loops, and artifacts. That’s what I’m exploring with PlanWeave: github.com/GaosCode/PlanW…

0 0 6 879 3

View Details

swift @gaoscode

3 months ago

@phuctm97 The problem with plan mode is that it stays linear. Real execution is a DAG: some tasks unblock others, some run in parallel, some loop back after review. A useful plan should become executable state.

0 0 0 851 2

View Details

swift @gaoscode

3 months ago

The basic idea is file-backed plan state: chat generates a plan, it becomes task graph + state files, each node carries prompt/dependencies/acceptance criteria/review gates/logs/status, and the UI reads/writes that state as an editable map. The graph becomes the source of truth for execution. This mockup is based on my OSS experiment planweave: github.com/GaosCode/PlanW…

3 4 10 941 31

View Details

swift @gaoscode

3 months ago

@thsottiaux Feature request: Plan Mode as durable execution state. Long tasks outgrow chat-text plans: progress, blockers, reviews, logs, and resume state drift. Let codex turn a plan into editable task graph/files with prompts, criteria, review gates, and resume. Mockup below.