191–200 of 603 posts
[flagged]
[flagged]
Which is ironically, the exact case those of us who don't find LLM-assisted coding "worth it" make.
Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…
Opus 4.6 is a jackass. It's got Dunning-Kruger and hallucinates all over the place. I had forgotten about the experience (as in the Gist above) of jamming on the escape key "no no no I never said to do that." But also I don't remember 4.5 being this bad.
But GPT 5.3 and 5.4 is a far more precise and diligent coding experience.
Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…
Earlier quoted context omitted.
This is really just how the tech industry works. We have abused the concept of consent into an absolute mess My personal favorite way they do this lately is notification banners for like... Registering for news letters "Would you like to sign up for our newsletter? Yes | Maybe Later" Maybe later being the only negative answer shows a pretty strong lack of understanding about consent!
Or the now-ubiquitous footer: "Store cookie? [Yes] [Ask me again]"
To 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…
The whole idea of just sending "no" to an LLM without additional context is kind of silly. It's smart enough to know that if you just didn't want it to proceed, you would just not respond to it. The fact that you responded to it tells it that it should do something, and so it looks for additional context (for the build mode change) to decide what to do.
It's not smart enough to know you would just not respond to it, not even close. It's been trained to do tasks in response to prompts, not to just be like "k, cool", which is probably the cause of this (egregious) error.
To 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…
If you forget to tell a team who the builder is going to be and forget to give them a workflow on how they should proceed, what can often happen is the team members will ask if they can implement it, they will give each other confirmations, and they start editing code over each other.
Hilarious to watch, but also so frustrating.
aside: I love using agent teams, by the way. Extremely powerful if you know how to use them and set up the right guardrails. Complete game changer.
Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…
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.
"The user said the exact word 'approved'. Implementing plan."
Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…
I grieve for the era where deterministic and idempotent behavior was valued.