[flagged]
Shall I implement it? No
241–250 of 603 posts
Re: Shall I implement it? No
#242I've had this or similar happen a few times
Re: Shall I implement it? No
#243Re: Shall I implement it? No
#244That'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
It does. But then, it's how i talk to myself. More generally, it's how i talk to people i trust the most. I swear curse and insult, it seems to shock people if they see me do it (to the llm). If i ask claude or chatgpt to summarize the tone and demeanor of my interactions, however, it replies "playful" which is how im actually using the "insults".
Politeness requires a level of cultural intuition to translate into effective action at best, and is passive aggressive at worst. I insult my llm, and myself, constantly while coding. It's direct, and fun. When the llm insults me back it is even more fun.
With my colleagues i (try to) go back to being polite and die a little inside. its more fun to be myself. maybe its also why i enjoy ai coding more than some of my peers seem to.
More likely im just getting old.
Re: Shall I implement it? No
#245[flagged]
It kinda... does? The problem is that folks have been flailing on the right UX for this.
This is what build vs. plan mode _does_ in OpenCode. OpenAI has taken a different approach in Codex, where Plan mode can perform any actions (it just has an extra plan tool), but in OC in plan mode, IIRC write operations are turned off.
The screenshot shows that the experience had just flipped from Plan to Build mode, which is why the system reminder nudged it into acting!
Now... I forget, but OC may well be flipping automatically when you accept a plan, or letting the model flip it or any other kind of absurdity, but... folks are definitely trying to do the approval split in-harness, they're just failing badly at the UX so far.
And I fully believe that Plan vs. Build is a roundly mediocre UX for this.
Re: Shall I implement it? No
#246Re: Shall I implement it? No
#247Its gotten so bad that Claude will pretend in 10 of 10 cases that task is done/on screenshot bug is fixed, it will even output screenshot in chat, and you can see the bug is not fixed pretty clear there. I consulted Claude chat and it admitted this as a major problem with Claude these days, and suggested that I should ask what are the coordinates of UI controls are on screenshot thus forcing it to look. So I did that…
> And on top of it, if you develop for native macOS, There’s no official tooling for visual verification. It’s like 95% of development is web and LLM providers care only about that.
I think this is built in to the latest Xcode IIRC
Re: Shall I implement it? No
#248Earlier quoted context omitted.
I've had some luck taming prompt introspection by spawning a critic agent that looks at the plan produced by the first agent and vetos it if the plan doesn't match the user's intentions. LLMs are much better at identifying rule violations in a bit of external text than regulating their own output. Same reason why they generate unnecessary comments no matter how many times you tell them not to.
How does one integrate critic agent to a Codex/Claude?
I just say something like "spawn an agent to review your plan" or something to that effect. "Red/green TDD" is apparently the nomenclature: https://simonwillison.net/guides/agentic-engineering-pattern...
I've also found it to be better to ask the LLM to come up with several ideas and then spawn additional agents to evaluate each approach individually.
I think the general problem is that context cuts both ways, and the LLM has no idea what is "important". It's easier to make sure your context doesn't contain pink elephants than it is to tell it to forget about the pink elephants.
Re: Shall I implement it? No
#249Its gotten so bad that Claude will pretend in 10 of 10 cases that task is done/on screenshot bug is fixed, it will even output screenshot in chat, and you can see the bug is not fixed pretty clear there. I consulted Claude chat and it admitted this as a major problem with Claude these days, and suggested that I should ask what are the coordinates of UI controls are on screenshot thus forcing it to look. So I did that…
>>It’s like 95% of development is web and LLM providers care only about that. I've been trying to use it for C++ development and it's maybe not completely useless, but it's like a junior who very confidently spouts C++ keywords in every conversation without knowing what they actually mean. I see that people build their entire companies around it, and it must be just web stuff, right? Claude just doesn't work for C++…
Models are also quite good at Go, Rust, and Python in my experience — also a lot of companies are using TypeScript for many non web related things now. Apparently they're also really good at C, according to the guy who wrote Redis anyway.
Re: Shall I implement it? No
#250Earlier quoted context omitted.
I've added an instruction: "do not implement anything unless the user approves the plan using the exact word 'approved'". This has fixed all of this, it waits until I explicitly approve.
"NOT approved!" "The user said the exact word 'approved'. Implementing plan."
Relevant comedy scene from Idiocracy (2006):