I read the first 5 paragraphs which were all "Noam", "Noam", "Noam" and then lost interest. The letter should have started by first acknowledging the heinous crimes committed against innocent children.
What crimes did Noam commit against children?? The only thing we know is that he got involved with Epstein. There’s no evidence or suggestion in anything that was divulged so far about Noam having been directly involved or even knowing about Epstein’s exploitation of young girls.
Very well written. Thank you for putting down your thoughts so succinctly; I'm often at a loss for words when I try to express the same thoughts in a coherent manner.
Recently, I have given up on writing unit tests, instead prompting an LLM to write them for me. I just sit back and keep prompting it until it gets it right. Sometimes it goes a little haywire in our Monorepo, but I don't have to accept its changes.
When I build unit tests around the right routines, I feel like all is right with the world. But some employers consider this gilding the lily.
But with LLMs in hand, I can generate entire suites of tests where they're most useful before management has the time to complain. All the little nice-to-have-but-hard-to-google environment tweaks are seconds away for the asking. It's finally cost effective to do things right.
I do it the other way around: I write the specs and unleash an agent to turn my test suite from red to green.
Each of us does half the work, the other half being done by a LLM. The difference is that I specify the desired behavior, while you leave the specification up to the LLM. A little strange if you ask me!
Same, and to avoid it going haywire I wrote an agents.md file with some prompts, like how to run a test for a single file and what to do before saying "I am done".
i think thats the best use you can get from LLM's in programming. Doing the boring simple test code that doesn't have to meet any quality requirements. Normally on a code review I ignore unit tests, written from humans oder LLM's out of this reason.
I tried teams, good way to burn all your tokens in a matter of minutes.
It seems that the Claude Code team has not properly taught Claude how to use teams effectively.
One of the biggest problems I saw with it is that Claude assumes team members are like a real worker, where once they finish a task they should immediately be given the next task. What should really happen is once they finish a task they should be terminated and a new agent should be spawned for the next task.
Unlike most normal people in the world, I was never taught how to tie shoelaces. And not because my parents and siblings did not try; but because I was too obstinate and wanted to do it my way! Needless to say I implemented a complicated knot that takes way too long and and a source of mockery. But it is my knot and I like it.
And they expect Google to pass it on to these people?
reply