Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gaslight-driven development

tonsky.me

Post reply on HN
Print view View original

91–100 of 113 posts

Re: Gaslight-driven development

#91

Post by stavros »

Dilettante_ wrote: post #90
stavros wrote: post #89

Earlier quoted context omitted.

Are you a teapot? If you were, maybe you'd be precious about people falsely claiming to be one too!

It's really more about how when I say "I am a teapot", I want people to think "Oh, he's a teapot!" and not "He might be a teapot, or he might be chiding me for misusing llms or he might be signaling that the monkey is out of bananas or [...]"

I agree, though that means I really should stop returning my 404 - Server Unavailable response, but you'll never have my 500 - OK.

Re: Gaslight-driven development

#93

Post by bjornsing »

PaulRobinson wrote: post #83
bjornsing wrote: post #51

This feels like the beginning of a wonderful friendship between me and the LLMS. I work as a fractional CTO. One of the things that frustrate me is when my clients have various idiosyncratic naming conventions on things, eg there’s a ”dev” and a ”prod” environment on AWS, but then there’s a ”test” and ”production” environment in Expo. It just needlessly consumes brain cycles, especially when you’re working with multi…

As the old joke goes: there are two hard problems in computer science - cache invalidation, naming things and off-by-one errors Naming things doesn’t get easier just because you bring an LLM to do it based on an incoherent stochastic process. Have you asked why those environments have not been renamed to align? As a former CTO I’d see it immediately as a signal of poor communication, poor standards adoption, or both.…

Sure, I can spend my days doing that. But I appreciate the help (from the LLMs). And I think we actually have the same goal function: we want to make naming more compressible, less unexpected. You can call that culture (and it is) but you can also see it as pure information theory.

Re: Gaslight-driven development

#94

Post by pas »

eggn00dles wrote: post #34
delifue wrote: post #20

> for example, we used tx.update for both inserting and updating entities, but LLMs kept writing tx.create instead. Guess what: we now have tx.create, too. If a function can both insert and update, it should be called "put". Using "update" is misleading.

put implies overwriting instead of updating. upsert is for you insert/update.

update already means overwriting.

semantically PUT is exactly upsert.

upsert is update + create if not exists, which is exactly PUT

any update without overwrite is "append" or "extend" (or something else)

Re: Gaslight-driven development

#95

Post by hi_hi »

Dilettante_ wrote: post #90
stavros wrote: post #89

Earlier quoted context omitted.

Are you a teapot? If you were, maybe you'd be precious about people falsely claiming to be one too!

It's really more about how when I say "I am a teapot", I want people to think "Oh, he's a teapot!" and not "He might be a teapot, or he might be chiding me for misusing llms or he might be signaling that the monkey is out of bananas or [...]"

What would be an appropriate response code for "He might be a teapot, or he might be chiding me for misusing llms or he might be signaling that the monkey is out of bananas or [...]"?

Re: Gaslight-driven development

#96

Post by Dilettante_ »

hi_hi wrote: post #95
Dilettante_ wrote: post #90

Earlier quoted context omitted.

It's really more about how when I say "I am a teapot", I want people to think "Oh, he's a teapot!" and not "He might be a teapot, or he might be chiding me for misusing llms or he might be signaling that the monkey is out of bananas or [...]"

What would be an appropriate response code for "He might be a teapot, or he might be chiding me for misusing llms or he might be signaling that the monkey is out of bananas or [...]"?

Each of those should have a clear, unique response code. There should be no "maybe it's this, maybe it's that". A real-world example is login forms that tell you something like "Invalid e-mail or password".

Are you joking around with me or is my point just not as obvious as I believed it to be?

Edit: Not sure if that last bit sounds confrontational, please know that it's a genuine question.

Re: Gaslight-driven development

#97

Post by bmicraft »

Dilettante_ wrote: post #84
hi_hi wrote: post #77

Earlier quoted context omitted.

I humbly request, if you are going to do this, please, please...use the 418 response. It deserves wider adoption :-)

Bit of a pet peeve: 418 is clearly defined as "I am a teapot", not "whatever I want it to mean". Please do not use it for anything other than its specified purpose, even if it is a joke.

If an LLM can hallucinate an endpoint, then the server is allowed to hallucinate being a teapot :)

Re: Gaslight-driven development

#98

Post by snickerdoodle12 »

trhway wrote: post #40
snickerdoodle12 wrote: post #33

Earlier quoted context omitted.

literally just turn on your blinkers, like you should be doing anyway, and lane assistant won't trigger. you are just outing yourself as a bad driver.

sorry, you're missing my point. I explicitly said that it isn't about the need to use blinkers.

And I say that makes no sense. If you use your blinkers, lane assist doesn't get in the way. So do what you should be doing anyway and use your blinkers.

Re: Gaslight-driven development

#99

Post by snickerdoodle12 »

bluefirebrand wrote: post #50
snickerdoodle12 wrote: post #33

Earlier quoted context omitted.

literally just turn on your blinkers, like you should be doing anyway, and lane assistant won't trigger. you are just outing yourself as a bad driver.

No, if you need to depart your lane in a hurry you cannot be expected to use the blinker first and the car should not fight you to do so

You are literally too lazy to move a single finger. You are a bad driver. Being "in a hurry" makes no sense either, turning on your blinkers should be ingrained in your muscle memory and take no additional effort.
Post reply on HN