This reminds me of when I tried to let Claude port an Android libgdx-based game to a WASM-based libgdx version, so I can play the game in the browser.

No matter how much I tried to force it to stick to a mostly line-by-line port, it kept trying to "improve" the code. At some point it had to undo everything as it introduced a number of bugs. I asked it: "What should I add to your prompt so you won't do this again?" and it gave me this:

  ### CRITICAL LESSON: Don't "Improve" During Porting
  -  **BIGGEST MISTAKE: Reorganizing working code**
    - **What I did wrong:** Tried to "simplify" by splitting `createStartButton()` into separate creation and layout methods
    - **Why it failed:** Introduced THREE bugs:
      1. Layout overlap (getY() vs getY() - getHeight())
      2. Children not sized (Group.setSize() doesn't affect children)
      3. Origins not updated (scaling animations broken)
    - **The fix:** Deleted my "improvements" and copied the original Android pattern faithfully
    - **Root cause:** Arrogance - assuming I could improve production-tested code without understanding all the constraints
    - **Solution:** **FOLLOW THE PORTING PRINCIPLES ABOVE** - copy first, don't reorganize
    - **Time wasted:** ~1 hour debugging self-inflicted bugs that wouldn't exist if I'd just copied the original
    - **Key insight:** The original Android code is correct and battle-tested. Your "improvements" are bugs waiting to happen.

I like the self-reflection of Claude, unfortunately even adding this to CLAUDE.md didn't fix it and it kept taking wrong turns so I had to abandon the effort.

▲ phpnode 6 hours ago | parent | next [-]

Claude doesn't know why it acted the way it acted, it is only predicting why it acted. I see people falling for this trap all the time

▲

kaffekaka 6 hours ago | parent | next [-]

Yes, this pitfall is a hard one. It is very easy to interpret the LLM in a way there is no real ground for.

▲

LoganDark 6 hours ago | parent | prev | next [-]

It's not even predicting why it acted, it's predicting an explanation of why it acted, which is even worse since there's no consistent mental model.

▲

nonethewiser 6 hours ago | parent | prev [-]

IDK how far AIs are from intelligence, but they are close enough that there is no room for anthropomorphizing them. When they are anthropomorphized its assumed to be a misunderstanding of how they work.

Whereas someone might say "geeze my computer really hates me today" if it's slow to start, and we wouldn't feel the need to explain the computer cannot actually feel hatred. We understand the analogy.

I mean your distinction is totally valid and I dont blame you for observing it because I think there is a huge misunderstanding. But when I have the same thought, it often occurs to me that people aren't necessarily speaking literally.

▲

amenhotep 5 hours ago | parent [-]

This is a sort of interesting point, it's true that knowingly-metaphorical anthropomorphisation is hard to distinguish from genuine anthropomorphisation with them and that's food for thought, but the actual situation here just isn't applicable to it. This is a very specific mistaken conception that people make all the time. The OP explicitly thought that the model would know why it did the wrong thing, or at least followed a strategy adjacent to that misunderstanding. He was surprised that adding extra slop to the prompt was no more effective than telling it what to do himself. It's not a figure of speech.

	▲	zarzavat 5 hours ago \| parent \| next [-]
		A good time to quote our dear leader: > No one gets in trouble for saying that 2 + 2 is 5, or that people in Pittsburgh are ten feet tall. Such obviously false statements might be treated as jokes, or at worst as evidence of insanity, but they are not likely to make anyone mad. The statements that make people mad are the ones they worry might be believed. I suspect the statements that make people maddest are those they worry might be true. People are upset when AIs are anthropomorphized because they feel threatened by the idea that they might actually be intelligent. Hence the woefully insufficient descriptions of AIs such as "next token predictors" which are about as fitting as describing Terry Tao as an advanced gastrointestinal processor.
	▲	phpnode 5 hours ago \| parent \| prev \| next [-]
		There's this underlying assumption of consistency too - people seem to easily grasp that when starting on a task the LLM could go in a completely unexpected direction, but when that direction has been set a lot of people expect the model to stay consistent. The confidence with which it answers questions plays tricks on the interlocutor.
	▲	nonethewiser 5 hours ago \| parent \| prev [-]
		Whats not a figure of speech? I am speaking general terms - not just this conversation here. The only specific figure of speech I see in the original comment is "self reflection" which doesn't seem to be in question here.

▲ everfrustrated 5 hours ago | parent | prev | next [-]

Worth pointing out that your IDE/plugin usually adds a whole bunch of prompts before yours - let alone the prompts that the model hosting provider prepends as well.

This might be what is encouraging the agent to do best practices like improvements. Looking at mine:

>You are a highly sophisticated automated coding agent with expert-level knowledge across many different programming languages and frameworks and software engineering tasks - this encompasses debugging issues, implementing new features, restructuring code, and providing code explanations, among other engineering activities.

I could imagine that an LLM could well interpret that to mean improve things as it goes. Models (like humans) don't respond well to things in the negative (don't think about pink monkeys - Now we're both thinking about them).

	▲	hombre_fatal 4 hours ago \| parent [-]
		It's also common for your own CLAUDE.md to have some generic line like "Always use best practices and good software design" that gets in the way of other prompts.

▲ wyldfire 4 hours ago | parent | prev | next [-]

One thing that might be effective at limited-interaction recovery-from-ignoring-CLAUDE.md is the code-review plugin [1], which spawns agents who check that the changes conform to rules specified in CLAUDE.md.

[1] https://github.com/anthropics/claude-code/blob/main/plugins/...

▲ 0x696C6961 7 hours ago | parent | prev | next [-]

I wish there was a feature to say "you must re-read X" after each compaction.

	▲	nickreese 7 hours ago \| parent \| next [-]
		Some people use hooks for that. I just avoid CC and use Codex.
	▲	philipp-gayret 5 hours ago \| parent \| prev \| next [-]
		There's no PostCompact hook unfortunately. You could try with PreCompact and giving back a message saying it's super duper important to re-read X, and hope that survives the compacting.
	▲	root_axis 3 hours ago \| parent \| prev [-]
		What would it even mean to "re-read after a compaction"?

▲ Lionga 6 hours ago | parent | prev [-]

Well its close to AGI, can you really expect AGI to follow simple instructions from dumbos like you when it can do the work of god?

	▲	b00ty4breakfast 6 hours ago \| parent [-]
		as an old coworker once said, when talking about a certain manager; That boy's just smart enough to be dumb as shit (The AI, not you; I don't know you well enough to call you dumb)