Summarizer

Input: I want to wash my car. The car wash is 50 meters away. Should I walk or drive? Output: Walk. It'll take you under a minute, and driving 50 meters barely gets the engine warm — plus you'd just have to park again at the other end. Honestly, by the time you started the car, you'd already be there on foot. --- I asked it to figure out why it made the mistake: "Physical/spatial common sense. Exactly what just happened — I pattern-matched "50 meters, walk vs drive" to a pedestrian trip and skipped the part where the car is the thing being transported. Similar traps: "I need to move this couch upstairs, should I take the elevator or stairs?" (the couch has to go with you), or anything where the object in the task needs to accompany you. Counting and letter-level operations. How many R's in "strawberry," counting words in a sentence, reversing strings. I process text as tokens, not characters, so these are surprisingly error-prone. Arithmetic at scale. Small sums are fine; multi-digit multiplication, long division, or anything requiring careful carrying is where I'll confidently produce a wrong answer. I should reach for a calculator and often don't. Recent events and live data. My training has a cutoff, and even after that I can be wrong about who currently holds a role, what a stock is worth, or whether a restaurant is still open. I should search more often than I do. Negation and constraint-stacking. "Name a movie that's not a sequel, not from the 2010s, not American, and has no dialogue" — the more filters, the more likely I quietly violate one. Your specific situation. I'll give generic advice when the right answer depends on details I didn't ask about. Sometimes I should stop and ask; often I don't. Confidently wrong on obscure specifics. Quoting a passage from a real book, citing a real paper's exact title, naming the B-side of a 1974 single — I'll often generate something plausible rather than admit I don't know. Taking a premise too literally. The car wash answer is a version of this: I answered the question as posed instead of stepping back to ask what you were actually trying to do. The meta-gotcha: I'm often most wrong when I sound most confident. If an answer comes out fast and tidy on a question that should be messy, that's a signal to push back."

Yea I’ve seen this and stopped it and asked it about it. Sometimes they notice bugs or issues and just completely ignore it.

I switched to Codex and found it extremely inferior for my use case. It is much faster, but faster worse code is a step in the wrong direction. You're just rapidly accumulating bugs and tech debt, rather than more slowly moving in the correct direction. I'm a big fan of Gemini in general, but at least in my experience Gemini Cli is VERY FAR behind either Codex or CC. It's both slower than CC, MUCH slower than Codex, and the output quality considerably worse than CC (probably worse than Codex and orders of magnitude slower). In my experience, Codex is extraordinarily sycophantic in coding, which is a trait that could t be more harmful. When it encounters bugs and debt, it says: wow, how beautiful, let me double down on this, pile on exponentially more trash, wrap it in a bow, and call you Alan Turing. It also does not follow directions. When you tell it how to do something, it will say, nah, I have a better faster way, I'll just ignore the user and do my thing instead. CC will stop and ask for feedback much more often. YMMV.

It's been shockingly bad for me - for another example when asked to make a new python script building off an existing one; for some cursed reason the model choose to .read() the py files, use 100 of lines of regex to try to patch the changes in, and exec'd everything at the end...

Hate that about Claude Code. I have been adding permissions for it to do everything that makes sense to add when it comes to editing files, but way too often it will generate 20-30 line bash snippets using sed to do the edits instead, and then the whole permission system breaks down. It means I have to babysit it all the time to make sure no random permission prompts pop up.

Still I don't previously remember Claude constantly trying to stop conversations or work, as in "something is too much to do", "that's enough for this session, let's leave rest to tomorrow", "goodbye", etc. It's almost impossible to get it do refactoring or anything like that, it's always "too massive", etc.

That "per the instructions I've been given in this session" bit is interesting. Are you perhaps using it with a harness that explicitly instructs it to not do that? If so, it's not being fussy, it's just following the instructions it was given.

It is the new "You are absolutely right!"

Maybe this? From the article: > Opus 4.7 is substantially better at following instructions. Interestingly, this means that prompts written for earlier models can sometimes now produce unexpected results: where previous models interpreted instructions loosely or skipped parts entirely, Opus 4.7 takes the instructions literally. Users should re-tune their prompts and harnesses accordingly.

> where previous models interpreted instructions loosely or skipped parts entirely, Opus 4.7 takes the instructions literally. Users should re-tune their prompts and harnesses accordingly. interesting

I like this in theory. I just hope it doesn't require you to be be as literal as if talking to a genie. But if it'll actually stick to the hard rules in the CLAUDE.md files, and if I don't have to add "DON'T DO ANYTHING, JUST ANSWER THE QUESTION" at the end of my prompt, I'll be glad.

coming more in line with codex - claude previously would often ignore explicit instructions that codex would follow. interested to see how this feels in practice I think this line around "context tuning" is super interesting - I see a future where, for every model release, devs go and update their CLAUDE.md / skills to adapt to new model behavior.

not a bot, voiced frustration is real here. I kind of depend on good LLMs now and wouldn't even mind if they had frozen the LLMs capabilities around dec 2025 forver and would hppily continue to pay, even more. but when suddenly the very same workload that was fine for months isn't possible anymore with the very same LLM out of nowhere and gets increasingly worse, its a huge disappointment. and having codex in parallel as a backup since ever I started also using it again with gpt 5.4 and it just rips without the diva sensitivity or overfitting into the latest prompt opus/sonnet is doing. GPT just does the job, maybe thinks a bit long, but even over several rounds of chat compression in the same chat for days stays well within the initial set of instructions and guardrails I spelled out, without me having to remind every time. just works, quietly, and gets there. Opus doesn't even get there anymore without nearly spelling out by hand manual steps or what not to do.

I don't use it for coding, but I do use it for real world tasks like general assistant. I did notice multiple times context rot even in pretty short convos, it trying to overachie and do everything before even asking for my input and forgetting basic instructions (For example I have to "always default to military slang" in my prompt, and it's been forgetting it often, even though it worked fine before)

You'd be surprised. With React, Claude can get twisted in knots mostly because React lends itself to a pile of spaghetti code.

I wonder if this one will be able to stop putting my fucking python imports inline LIKE I'VE TOLD IT A THOUSAND TIMES.