My best advise as #SoftwareEngineer, be humble. So many people will take the dive to the bottom of the ocean and in a lifetime one may never reach the bottom. Thereβs just so much knowledge and wisdom in this profession. #javascript#react#nodejs#webpack#babel#nginx#debian
Had to use claude code to create everything I wanted inside of Hermes. One idea turned into multiple iterations and hours configuring it. Claude code completed everything. While grok failed.
Block recently laid off 40% of its workforce.
I am truly sorry to everyone going through this. We want to provide a bit of support during this difficult time. We would like to offer one year of free access to our interview prep platform. Losing a job is incredibly stressful, and we hope this can ease at least one small part of the process.
Our platform covers system design, coding patterns, ML system design, OOD, and more.
There are no strings attached.
Just email me at [email protected] with your name and a brief note, and we will get you set up.
what are your results using OpenClaw with grok-4-1-fast-reasoning? It keeps giving a sense of things are correct when in reality things are erroring out.
Anthropic had 16 AI agents build a C compiler from scratch. 100k lines, compiles the Linux kernel, $20k, 2 weeks.
To put that in perspective GCC took thousands of engineers over 37 years to build. (Granted from 1987 - however) One researcher and 16 AI agents just built a compiler that passes 99% of GCC's own torture test suite, compiles FFmpeg, Redis, PostgreSQL, QEMU and runs Doom.
They say they "(mostly) walked away." But that "mostly" is doing heavy lifting.
No human wrote code but the researcher constantly redesigned tests, built CI pipelines when agents broke each other's work, and created workarounds when all 16 agents got stuck on the same bug.
The human role didn't disappear. It shifted from writing code to engineering the environment that lets AI write code.
I donβt know how you could make the point AI is hitting a wall.