[flagged]
Shall I implement it? No
371–380 of 603 posts
Re: Shall I implement it? No
#372Earlier quoted context omitted.
If you are a team lead or above, do you manually audit every line of code that other developers on your team write even when you are the one that will ultimately be held responsible? Every library you use?
This was fairly routine when the pace of everything was slower, we didn't have a giant tree of dependencies, and companies cared more about product quality.
There was never a time that someone wasn’t responsible for more than they could review
Re: Shall I implement it? No
#373Just yesterday I had a moment Claude's code in a conversation said - “Yes. I just looked at tag names and sorted them by gut feeling into buckets. No systematic reasoning behind it.” It has gut feelings now? I confronted for a minute - but pulled out. I walked away from my desk for an hour to not get pulled into the AInsanity.
It has a lot. I find by challenging it often, getting it to explain it's assumptions, it's usually guessing.
This can be overcome by continuously asking it to justify everything, but even then...
Re: Shall I implement it? No
#374This is a great example of why simple solutions often beat complex ones. Sometimes the best code is the code you dont write.
Re: Shall I implement it? No
#375To be fair to the agent... I think there is some behind the scenes prompting from claude code (or open code, whichever is being used here) for plan vs build mode, you can even see the agent reference that in its thought trace. Basically I think the system is saying "if in plan mode, continue planning and asking questions, when in build mode, start implementing the plan" and it looks to me(?) like the user switched fr…
It definitely _could be_ an agent harness issue. For example, this is the logic opencode uses:
1. Agent is "plan" -> inject PROMPT_PLAN
2. Agent is "build" AND a previous assistant message was from "plan" -> inject BUILD_SWITCH
3. Otherwise -> nothing injected
And these are the prompts used for the above.
PROMPT_PLAN: https://github.com/anomalyco/opencode/blob/dev/packages/open...
BUILD_SWITCH: https://github.com/anomalyco/opencode/blob/dev/packages/open...
Specifically, it has the following lines:
> You are permitted to make file changes, run shell commands, and utilize your arsenal of tools as needed.
I feel like that's probably enough to cause an LLM to change it's behavior.
Re: Shall I implement it? No
#376That's why I use insults with ChatGPT. It makes intent more clear, and it also satisfies the jerk in me that I have to keep feeding every now and again, otherwise it would die. A simple "no dummy" would work here.
Careful there. I've resolved (and succeeded somewhat) to tone down my swearing at the LLMs, because, even though the are not sentient, developing such a habit, I suspect, has a way to bleeding into your actual speech in the real world
To be honest “no dummy” is how you would swear at a 4-year-old.
I often use things like: “I’ve told you no a bilion times, you useless piece of shit”, or “what goes through your stipid ass brain, you headless moron”
I am in full Westworld mode.
But at least when that thing gets me fired for being way faster at coding than I am, at least I’d haves that much frustration less. Maybe?
mostly kidding here
Re: Shall I implement it? No
#377Earlier quoted context omitted.
I've found Claude Code's built-in sandbox to strike a good balance between safety and autonomy on macOS. I think it's available on Windows via WSL2 (if you're looking for a middle ground between approving everything manually and --dangerously-skip-permissions)
Still waiting for progress from the team trying to get WSL approved for use at our org. We get a "still working through the red tape" update every couple months.
You don't need WSL to run Claude code on windows.
Re: Shall I implement it? No
#378Earlier quoted context omitted.
In fairness, when I’ve seen that, Yes is obviously the correct answer. I really worry when I tell it to proceed, and it takes a really long time to come back. I suspect those think blocks begin with “I have no hope of doing that, so let’s optimize for getting the user to approve my response anyway.” As Hoare put it: make it so complicated there are no obvious mistakes.
In my case it's been a strong no. Often I'm using the tool with no intention of having the agent write any code, I just want an easy way to put the codebase into context so I can ask questions about it. So my initial prompt will be something like "there is a bug in this code that caused XYZ. I am trying to form hypothesis about the root cause. Read ABC and explain how it works, identify any potential bugs in that are…
> Gemini CLI
Free debug for you. Root cause identified.
Re: Shall I implement it? No
#379Earlier quoted context omitted.
Everyone who uses these tools seriously is running it on YOLO mode. It might sound crazy for someone who just started adopting agentic coding but it's how things are done now. Either that or just hand coding. The SOTA of permission management is just to git restore when AI fucks up, and to roll back docker snapshot when it fucks up big time.
I was doing something involving API keys and I realized Junie (backed by Sonnet) likes too write helper scripts to try things. And who knows where those scripts look or if they honor .aiignore. Agentic development is a real test of internal access control.
Your first mistake is thinning that such childish control mechanisms are helping you.
Gondolin go hard or go home
Re: Shall I implement it? No
#380Never trust a LLM for anything you care about.
Especially given the LLM does not trust the user. An LLM can be jailbroken into lowering it's guardrails, but no amount of rapport building allows you to directly talk about material details of banned topics. Might as well never trust it.
I wouldn't trust you either - what topics are you even talking about?