undefined | Better HN

0 pointsantdke14d ago0 comments

Yeah, anyone who’s used LLMs for a while would know that this conversation is a lost cause and the only option is to start fresh.

But, a common failure mode for those that are new to using LLMs, or use it very infrequently, is that they will try to salvage this conversation and continue it.

What they don’t understand is that this exchange has permanently rotted the context and will rear its head in ugly ways the longer the conversation goes.

0 comments

hedora14d ago

I’ve found this happens with repos over time. Something convinces it that implementing the same bug over and over is a natural next step.

I’ve found keeping one session open and giving progressively less polite feedback when it makes that mistake it sometimes bumps it out of the local maxima.

Clearing the session doesn’t work because the poison fruit lives in the git checkout, not the session context.

ex-aws-dude14d ago

I like how anything these tools do wrong just boils down to “you’re using it wrong”

It can do no wrong

It is unfalsifiable as a tool

retsibsi14d ago

I don't think it's intended as that kind of binary. It's more like "yeah, it's flawed in that way, and here's how you can get around that". If someone's claiming the tool is perfect, they're wrong; but if someone's repeatedly using it in the way that doesn't work and claiming the tool is useless, they're also wrong.

planb14d ago

Nobody said that. But as you say, it's just a tool. Tools need to be used correctly. If tools are unintuitive, maybe that's due to the nature of the tool or due to a flaw in it's design. But either way, you as the user need to work around that if you want to get the maximum use out of the tool.

j / k navigate · click thread line to collapse