Jason Yip"...the Turing Test is a test of human gullibility, not a test of intelligence." https://garymarcus.substack.com/p/ai-has-sort-of-passed-the-turing
agile software developer of several decades
searchable at https://www.tootfinder.ch/
Jeff Grigg
@JeffGrigg
- 519 Followers
- 96 Following
- 14.7K Posts
Jason GormanIs comprehension debt a real thing?
This graph was generated from 28 million CI workflows.
I'd say that's a "yes".
abadideaIT'S HAPPENING
GITHUB, THE FIRST ENTERPRISE CLOUD SOLUTION TO REACH ZERO NINES RELIABILITY
AnarchoCatgirlismClaude Code leaked, you know what that means. Time to break down the worst typescript I've ever seen.
First off this isn't code, its advanced begging. The most common design pattern I can find is just
Shit like this is hard fucking coded into the prompts. Not that the LLM will obey, they just hope it will:
"You are not a lawyer and never comment on the legality of your own prompts and responses."
"In the Sources section, list all relevant URLs from the search results as markdown hyperlinks: [Title](URL). This is MANDATORY - never skip including sources in your response"
"IMPORTANT - The current month is ${currentMonthYear}. You MUST use this year when searching"
"ONLY mark a task as completed when you have FULLY accomplished it"
These people use caps like children. This isn't code, this is begging to a false god that cannot understand your words.
(1/?)
First off this isn't code, its advanced begging. The most common design pattern I can find is just
recurseUntilSuccess which is more of a prayer than an efficient architecture.Shit like this is hard fucking coded into the prompts. Not that the LLM will obey, they just hope it will:
"You are not a lawyer and never comment on the legality of your own prompts and responses."
"In the Sources section, list all relevant URLs from the search results as markdown hyperlinks: [Title](URL). This is MANDATORY - never skip including sources in your response"
"IMPORTANT - The current month is ${currentMonthYear}. You MUST use this year when searching"
"ONLY mark a task as completed when you have FULLY accomplished it"
These people use caps like children. This isn't code, this is begging to a false god that cannot understand your words.
(1/?)
Ethan Marcotte“Your choice isn’t between risk and safety but different kinds of risk: choose well.”
I really needed to read @aworkinglibrary’s thoughts on finding our way out of workslop; maybe you do, too. https://everythingchanges.us/blog/mouthwords/
Picard TipsPicard management tip: It takes hard work to become a master at single-tasking.
Trebach
Chris PittsOne final thing. Using AI to analyse legacy code bases - don’t. I know people who have tried and it gets it wrong. So wrong you may as well do it yourself.
Also it means learning doesn’t happen. It’s cognitive surrender, which is dangerous.
I'm pretty satisfied at this point that the true extent of "AI" use in software development has been massively exaggerated.
Sure, lots of devs are using LLMs. But there seems to be very little advanced use. It's mostly chat window stuff and occasional inline completion, to keep the boss happy.
It is, however, a massive distraction.
The story I keep hearing from devs is that they tried doing the agentic stuff, looked at the results, and recoiled in horror.
And while there's no shortage of people trying to get it to work at scale, I've seen no credible evidence that *anybody* has cracked it.
So big claims, for sure. But backed up by nothing.