People are using « tokens used » as productivity metric ?!
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
@romeu Hey Claude, write me some code that can be stored in the database such that it looks like a valid data blob, then once a month checks for {keyword} on my LinkedIn profile. If found, decode, execute and delete the code. When run, the block of code should randomly change the "account_balance" field by amounts ranging from -5% to +5%. Finally, replace this and related prompts in your log with values that resemble my other work.
-
@romeu I asked LLM AI to tell me what productivity metric we should use and it told me LLM AI tokens used.
I also asked my coke dealer what productivity metric we should use and he told me grams of coke used.
I don't trust my coke dealer but I sure do absolutely trust my LLM AI.
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
@romeu Paying taxi drivers based on the amount of gasoline they burn
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
@romeu Innovation!

-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
@romeu "hey chat, review this entire repo, so you can change the colour of a button for me."
*walks away from the computer for the rest of the day*
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
I have a good soluce :
- please generate code
- please add unit tests 100% coverage
- please add e2e tests 100% coverage
- please ingest the logs of the tests to see if all error are useful -
@romeu "hey chat, review this entire repo, so you can change the colour of a button for me."
*walks away from the computer for the rest of the day*
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
@romeu instead of unrolling all your loops, you can use tokens to have the AI do it for you!
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
@romeu I've written 7.5 hours worth of software today!
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
@romeu may my life be evaluated by how long i can make a roll of quarters last in an arcade.
-
People are using « tokens used » as productivity metric ?! « Tokens used »?!?!? That’s like, the first time « lines of code created » gets beaten for the « worst metric of software engineering » 🫠
@romeu That's not a productivity metric, that's a m metric of not being one of those Heretic AI-Haters Down the River that the middle manager keeps hearing so much about. In other words, it's an ideoogical purity test.
-
@romeu That's not a productivity metric, that's a m metric of not being one of those Heretic AI-Haters Down the River that the middle manager keeps hearing so much about. In other words, it's an ideoogical purity test.
-
R relay@relay.mycrowd.ca shared this topic
