[ericol]

I did some work yesterday with Opus and found it amazing.

Today we are almost on non-speaking terms. I'm asking it to do some simple stuff and he's making incredible stupid mistakes:

    This is the third time that I have to ask you to remove the issue that was there for more than 20 hours. What is going on here?

and at the same time the compacting is firing like crazy. (What adds ~4 minute delays every 1 - 15 minutes)

  | # | Time     | Gap before | Session span | API calls |
  |---|----------|-----------|--------------|-----------|
  | 1 | 15:51:13 | 8s        | <1m          | 1         |
  | 2 | 15:54:35 | 48s       | 37m          | 51        |
  | 3 | 16:33:33 | 2s        | 19m          | 42        |
  | 4 | 16:53:44 | 1s        | 9m           | 30        |
  | 5 | 17:04:37 | 1s        | 17m          | 30        |
  # — sequential compaction event number, ordered by time.

  Time — timestamp of the first API call in the resumed session, i.e. when the new context (carrying the compaction summary) was first sent to the
  model.

  Gap before — time between the last API call of the prior session and the first call of this one. Includes any compaction processing time plus user
   think time between the two sessions.

  Session span — how long this compaction-resumed session ran, from its first API call to its last before the next compaction (or end of session).

  API calls — total number of API requests made during this resumed session. Each tool use, each reply, each intermediate step = one request.

Bottomline, I will probably stay on Sonnet until they fix all these issues.

[losvedir]

> This is the third time that I have to ask you to remove the issue that was there for more than 20 hours. What is going on here?

I don't know if you're giving this as something you've actually given Claude, but I don't think it's a good way of using Claude.

It's not a collaborator who's having a bad day where a little empathy might make him feel better and realize his error. It's a token generator based on a prompt which includes all chat history. If you have three examples of the bad approach in the history, in a format that looks like Claude doing work, it will totally pollute it! And even worse with auto-compaction where you don't know exactly what of those false starts is getting summarized into its context.

You have to treat this like a tool and understand how it works.

If Claude is going down a wrong path it's better to cancel and rewind and improve the previous addition to the prompt. You don't want it to generate a bunch of misleading tokens for itself and leave it in the context window indefinitely!

[ericol]

> I don't know if you're giving this as something you've actually given Claude, but I don't think it's a good way of using Claude.

That wasn't the full prompt, I trimmed it for clarity, but I agree with everything you said and that's how I actually use it.

I have a proxy logging everything sent to and from Claude in a structured way, which is precisely what let me do that compaction analysis in the first place.

When Claude goes off track, I don't tell it "you did something wrong". I ask it to analyze the tool outputs and the exchange so far and let it reconcile the discrepancy itself. That tends to work better than narrating the error to it.

The venting messages like that one are honestly for me, not for Claude. I know it's a tool. But it also behaves and communicates like a person, and that's a design choice that comes from Anthropic, not from me. What I've found is that writing something like that and then following it with proper instructions works fine in practice: Claude either ignores the venting or briefly acknowledges it and moves on. The actual output isn't affected. It's just how I process frustration without breaking the workflow.

[j_bum]

Yep I bewilders me when I see instructions like this. Go bad and edit your previous message if you didn’t et what you want!

I think this is a direct result of OpenAI and Anthropic humanizing these models too much.

I want C-3PO by my side helping me work, not a machine acting emotional.

But that’s what they’ve given us, and now a huge fraction of the username treats these tools like a human.

[aulin]

They won't. These are not "issues", it's them trying to push the models to burn less compute. It will only get worse.

[criemen]

> it's them trying to push the models to burn less compute

I'm curious, how does using more tokens save compute?

[BoorishBears]

I'm 99.9% sure Opus 4.7 is a smaller model than 4.6.

Too many signs between the sudden jump in TPS (biggest smoking gun for me), new tokenenizer, commentary about Project Mythos from Ant employees, etc.

It looks like their new Sonnet was good enough to be labeled Opus and their new Opus was good enough to be labeled Mythos.

They'll probably continue post-training and release a more polished version as Opus 5

[b65e8bee43c2ed0]

productivity (tokens per second per hardware unit) increases at the cost of output quality, but the price remains the same.

both Anthropic and OpenAI quantize their models a few weeks after release. they'd never admit it out loud, but it's more or less common knowledge now. no one has enough compute.

[sthimons]

Pretty bold claim - you have a source for that?

[Rapzid]

There is no evidence TMK that the accuracy the models change due to release cycles or capacity issues. Only latency. Both Anthropic and OpenAI have stated they don't do any inference compute shenanigans due to load or post model release optimization.

Tons of conspiracy theories and accusations.

I've never seen any compelling studies(or raw data even) to back any of it up.

[cebert]

Do you have a source for that claim?

[b65e8bee43c2ed0]

my source is that people have been noticing this since GPT4 days.

https://arxiv.org/pdf/2307.09009

but of course, this isn't a written statement by a corporate spokespersyn. I don't think that breweries make such statements when they water their beer either.

[shortstuffsushi]

I think that the idea is each action uses more tokens, which means that users hit their limit sooner, and are consequently unable to burn more compute.

[ryanschaefer]

What?

[bloppe]

It could be the adaptive reasoning

[rustyhancock]

If you've not seen Common People Black Mirror episode I strongly recommend it.

The only misprediction it makes is that AI is creating the brain dead user base...

You have to hook your customers before you reel them in!

https://www.netflix.com/gb/title/70264888?s=a&trkid=13747225...

[cadamsdotcom]

> he’s making .. mistakes

Claude and other LLMs do not have a gender; they are not a “he”. Your LLM is a pile of weights, prompts, and a harness; anthropomorphising like this is getting in the way.

You’re experiencing what happens when you sample repeatedly from a distribution. Given enough samples the probability of an eventual bad session is 100%.

Just clear the context, roll back, and go again. This is part of the job.

[yokoprime]

Why be so upset at someone using pronouns with a LLM?

[ericol]

You are being downvoted but I actually agree with your statement.

[solenoid0937]

This is not how AI works man. Speaking condescendingly or sternly to it WILL result in worse output. Imagine if you spoke to an intern like that, would they make more or less mistakes after?

You should just revert the context and provide more detail and rationale in the message.

[whalesalad]

I am having a shit experience lately. Opus 4.7, max effort.

> You're right, that was a shit explanation. Let me go look at what V1 MTBL actually is before I try again.

> Got it — I read the V1 code this time instead of guessing. Turns out my first take was wrong in an important way. Let me redo this in English.

:facepalm:

[tremon]

> I read the V1 code this time instead of guessing

Does the LLM even keep a (self-accessible) record of previous internal actions to make this assertion believable, or is this yet another confabulation?

[cheesecakegood]

No they do not (to be clear, not internal state, just the transcript). It’s entirely role-play. LLM apologies are meaningless because the models are mostly stateless. Every new response is a “what would a helpful assistant with XYZ prior context continue to say?”

[radlad]

Yes, the LLM is able to see the entire prior chat history including tool use. This type of interaction occurs when the LLM fails to read the file, but acts as though it had.

[al_borland]

This seems like the experience I've had with every model I've tried over the last several years. It seems like an inherent limitation of the technology, despite the hyperbolic claims of those financially invested in all of this paying off.

[smt88]

Opus 4.6 pre-nerf was incredible, almost magical. It changed my understanding of how good models could be. But that's the only model that ever made me feel that way.

[whalesalad]

Yes! I genuinely got a LOT of shit done with Opus 4.6 "pre nerf" with regular old out-of-the-box config, no crazy skills or hacks or memory tweaks or anything. The downfall is palpable. Textbook rugpull.

[solenoid0937]

There was no nerf - this meme needs to die.

[smt88]

What exactly happened then? How did we all have this collective hallucination?

[ec109685]

Did they nerf the model or was it changes to Claude code? I agree it got frustrating.

[al_borland]

That was better, but still not to the point that I just let it go on my repo.

[ed_elliott_asc]

If it isn’t working for you why don’t you choose an older model? 4.6

[ericol]

Matches what I am experiencing. Makes incredible stupid mistakes.

The weird stuff is yesterday I asked it to test and report back on a 30+ commit branch for a PR and it did that flawlessly.

[alphabettsy]

The docs suggest not using max effort in most cases to avoid overthinking :shrug:

[whalesalad]

They've jumped the shark. I truly can't comprehend why all of these changes were necessary. They had a literal money printing machine that actually got real shit done, really well. Now it's a gamble every time and I am pulling back hard from Anthropic ecosystem.

[solenoid0937]

it's clearly all in your head. 4.6 is just as capable as it used to be. literally no one on the internet has managed to post credulous and real evidence of a nerf

this is just another trendy conspiracy theory that people reinforce because of selection/recency bias. you hear "nerf", your brain overindexes on the next time Claude does poorly. it is the same phenomenon when you notice a new vocabulary word all the time.

[geraldwhen]

It seems clear that it was a money spending machine, not a money printing machine.