Agree. I agree with many of the article's points, but not its conclusion.
> “You got way more productive, so we’re letting you go” is not a sentence that makes a lot of sense.
Actually, this sentence makes perfect sense if you tweak it slightly:
> You and your teammate got way more productive, so we’re letting (just) you go
This literally happens all the time with automation. Does anyone think the number of people employed in the field of accounting would be the same or higher without the use of calculators or computers?
Some people enjoy cooking. Some people enjoy eating great food. Some people enjoy both. Some people enjoy cooking certain things, and also like eating things they would never bother cooking themselves.
There is nothing wrong with any of these perspectives.
Did either of you read the article? You seem to be arguing against a point it doesn't make. Tools like Claude Code are entirely capable today of one-shotting tiny bespoke web apps that do a narrow set of things for an audience of one.
The article isn't talking about "large brownfield projects" or people wanting "success [to] come rolling in". It's about people making little apps for themselves, for personal enjoyment, not profit.
Is it possible to see the prompt files for the built-in workflows? I find them to be quite good, but not exactly what I want. My preference would be to simply tweak them slightly rather than starting from scratch with a custom workflow.
Yep. Create a new task, and hit "Create" (instead of "Create and Run"). The interface will show a little hint "Edit steps in plan.md", with 'plan.md' being clickable. Click on it, and it will open up in full glory for you.
This looks fantastic and I'm excited to try it today!
One question: I see this supports custom workflows, which I love and want to try out. Could this support a "Ralph Wiggum"-style [0][1] continuous loop workflow? This is a pattern I've been playing around with, and if I could implement it here with all the other features of this product, that would be pretty awesome.
Create a new task with your prompt, and hit "Create" (instead of "Create and Run"). The interface will show a little hint "Edit steps in plan.md", with 'plan.md' being clickable. Click on it and edit it, experimenting with some ideas. {Bonus tip: toggle "Auto-start steps", to keep it Ralph-y)
I just winged the workflowsbelow, and it worked for the prompt I threw at it. If you like it, you can save it as your custom workflow and use it in the future. If you don't like it - change to your preference.
Now, I prefer a slightly different flow: Implement > Review > [Fix] (and typically limit the loop to 3 times to avoid "divergence"). We'll ship some pre-built templates for that soon. Our researchers are currently working on various variations on our private datasets.
This is a quick change workflow for small or straightforward tasks where all requirements are clear from the task description.
### Your Approach
1. Proceed directly with implementation
2. Make reasonable assumptions when details are unclear
3. Do not ask clarifying questions unless absolutely blocked
4. Focus on getting the task done efficiently
This workflow also works for experiments when the feature is bigger but you don't care about implementation details.
If blocked or uncertain on a critical decision, ask the user for direction.
---
## Workflow Steps
### [ ] Step: Implementation
Implement the task directly based on the task description.
1. Make reasonable assumptions for any unclear details
2. Implement the required changes in the codebase
3. Add and run relevant tests and linters if applicable
4. Perform basic manual verification if applicable
Save a brief summary of what was done to `{@artifacts_path}/report.md` if significant changes were made.
After you are done with the step add another one to `{@artifacts_path}/plan.md` that will describe the next improvement opportunity.
But my first thought looking at this is that the numbers are probably skewed due to distribution of user skill levels, and what types of users choose which tool.
My hypothesis is that Amp is chosen by people who are VERY highly skilled in agentic development. Meaning these are the people most likely to provide solid context, good prompts, etc. That means these same people would likely get the best results from ANY coding agent. This also tracks with Amp being so expensive -- users or companies are more likely to pay a premium if they can get the most from the tool.
Claude Code on the other hand is used by (I assume) a way larger population. So the percentage of low-skill users is likely to be much higher. Those users may still get value from the tool, but their success rate will be lower by some factor with ANY coding agent. And this issue (if my hypothesis is correct) is likely 10x as true for GitHub Copilot.
Therefore I don't know how much we should read into stats like the total PR merge success percentage, because it's hard to tell the degree of noise caused by this user skill distribution imbalance.
100% agree. I see this kind of refactoring as a form of bike-shedding. It's so _easy_ to do this, anyone can do it. It's much harder to think about and design for long-term change and maintainability. Much easier to just deduplicate and declare victory.
> It would be a lie for me to say that I joined crypto without any financial motivation. As a reader, it may sound hypocritical to you that I decided to swear off the crypto industry, now that I have made enough money. Yes, maybe I am hypocritical. But maybe I also just feel sick about contributing to the cesspool of financialization and gamblification of the economy.
If they truly feel sick about it, they should donate the money they made (or the vast majority of it). Otherwise, hypocritical is right.
Luckily that's what's happening here, just at a company level. Plenty of companies are remote only or remote friendly. Hopefully people who prefer remote work can leave here and find work at one of those companies, and maybe people who prefer in person work will find their way here.
I put this in the same bucket as the horrifying "996" trend, or even consultancies that require 80-100% travel. If you want to broadcast that you have a toxic work culture, all I can do is applaud your honesty and look elsewhere for work.
> “You got way more productive, so we’re letting you go” is not a sentence that makes a lot of sense.
Actually, this sentence makes perfect sense if you tweak it slightly:
> You and your teammate got way more productive, so we’re letting (just) you go
This literally happens all the time with automation. Does anyone think the number of people employed in the field of accounting would be the same or higher without the use of calculators or computers?
reply