https://www.askmodu.com/rankings independently aggregates traffic from a variety of agents and amp consistently has the highest success rate for small and large tasks
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.
The co-diagnosis of autism and ADHD became possible with the DSM-5 in 2013. According to the scientific literature, 50 to 70% of individuals with autism spectrum disorder (ASD) also present with comorbid attention deficit hyperactivity disorder (ADHD).
Interesting the paid functionality is on the old web stack "We're upgrading our historical data systems to improve their security, stability and resilience. During the upgrade some data will not be available, we aim to restore full access by mid-2026."
> the cost breakdown included $4.1 million for the redesign, $79.8 million for the website build, and the site's launch and security testing cost $12.6 million.
> “Additional features, security testing and preparedness for website launch cost $12.6 million. This includes the build, test and deployment of feature releases, and performance and load testing to ensure the website can accommodate peak volumes of traffic we see during severe weather.”
Wow thank you. That's really expensive if it's just for the website displaying the processed data.
I just looked up the cost of the recent redesign of the weather service in my small country of Switzerland. And I don't think more than 10 times the cost can be explained by the size of the country.
The redesign of the website of the website of the weather service in my small country cost about $6-7 million and the project planning was $600'000. It seems like they hired the same company that did the previous website which makes sense since they spent the previous 10 years keeping it running.
https://www.anthropic.com/engineering/advanced-tool-use talks more about the why