My productivity with agentic tools is roughly 33% higher than last year without them, measured by models, features, and milestones delivered.
Concept to deliverable is roughly 3x faster, with better quality—not limited to coding, but also decision-making.
What matters most is not whether the tools are agentic, but rigorously following the “algorithm”:
- Make requirements less dumb
- Delete the part or process step
- Optimize
- Accelerate
- Automate
Agentic is the last step. Deploying it too early only increases the velocity of slop. Routine housecleaning keeps agentic tools effective.
Given the pace of model improvements, I cannot imagine what work will look like soon.
El cambio de FSD a TAD me provoca TOC. Todo va en grupos de 3 letras…. Al final el problema europeo es de semántica. Mismo producto, distinto nombre, cuela. En Europa conviven muchas lenguas y el inglés no es la dominante. Acaso en España deberíamos llamarlo CTA? #tesla#fsd
GLM-5.3 has helped defend 389 open-source projects, with 4,249 potential vulnerabilities found so far.
OpenVuln is still running. The service remains free, and findings go privately to maintainers.
https://t.co/wqRE3zC2b5