> Long-running conversations and agentic tasks often hit the context window. Context compaction automatically summarizes and replaces older context when the conversation approaches a configurable threshold, letting Claude perform longer tasks without hitting limits.
Not having to hand roll this would be incredible. One of the best Claude code features tbh.
Curious how long it typically takes for a new model to become available in Cursor?
Take critical thinking — genuinely questioning your own assumptions, noticing when a framing is wrong, deciding that the obvious approach to a problem is a dead end. Or creativity — not recombination of known patterns, but the kind of leap where you redefine the problem space itself. These feel like they involve something beyond "predict the next token really well, with a reasoning trace."
I'm not saying LLMs will never get there. But I wonder if getting there requires architectural or methodological changes we haven't seen yet, not just scaling what we have.
Nowadays, I have often seen LLMs (Opus 4.5) give up on their original ideas and assumptions. Sometimes I tell them what I think the problem is, and they look at it, test it out, and decide I was wrong (and I was).
There are still times where they get stuck on an idea, but they are becoming increasingly rare.
Therefore, think that modern LLMs clearly are already able to question their assumptions and notice when framing is wrong. In fact, they've been invaluable to me in fixing complicated bugs in minutes instead of hours because of how much they tend to question many assumptions and throw out hypotheses. They've helped _me_ question some of my assumptions.
They're inconsistent, but they have been doing this. Even to my surprise.
yet - given an existing codebase (even not huge) they often won't suggest "we need to restructure this part differently to solve this bug". Instead they tend to push forward.
Having realized that, perhaps you are right that we may need a different architecture. Time will tell!
I don't think there's anything you can't do by "predicting the next token really well". It's an extremely powerful and extremely general mechanism. Saying there must be "something beyond that" is a bit like saying physical atoms can't be enough to implement thought and there must be something beyond the physical. It underestimates the nearly unlimited power of the paradigm.
Besides, what is the human brain if not a machine that generates "tokens" that the body propagates through nerves to produce physical actions? What else than a sequence of these tokens would a machine have to produce in response to its environment and memory?
Ah yes, the brain is as simple as predicting the next token, you just cracked what neuroscientists couldn't for years.
Couple that with all the automatic processes in our mind (filled in blanks that we didn't observe, yet will be convinced we did observe them), hormone states that drastically affect our thoughts and actions..
and the result? I'm not a big believer in our uniqueness or level of autonomy as so many think we have.
With that said i am in no way saying LLMs are even close to us, or are even remotely close to the right implementation to be close to us. The level of complexity in our "stack" alone dwarfs LLMs. I'm not even sure LLMs are up to a worms brain yet.
Have you tried actually prompting this? It works.
They can give you lots of creative options about how to redefine a problem space, with potential pros and cons of different approaches, and then you can further prompt to investigate them more deeply, combine aspects, etc.
So many of the higher-level things people assume LLM's can't do, they can. But they don't do them "by default" because when someone asks for the solution to a particular problem, they're trained to by default just solve the problem the way it's presented. But you can just ask it to behave differently and it will.
If you want it to think critically and question all your assumptions, just ask it to. It will. What it can't do is read your mind about what type of response you're looking for. You have to prompt it. And if you want it to be super creative, you have to explicitly guide it in the creative direction you want.
In my experience, if you do present something in the context window that is sparse in the training, there's no depth to it at all, only what you tell it. And, it will always creep towards/revert to the nearest statistically significant answers, with claims of understanding and zero demonstration of that understanding.
And, I'm talking about relatives basic engineering type problems here.
But I may easily be massively underestimating the difficulty. Though in any case I don't think it affects the timelines that much. (personal opinions obviously)
> Prefilling assistant messages (last-assistant-turn prefills) is not supported on Opus 4.6. Requests with prefilled assistant messages return a 400 error.
That was a really cool feature of the Claude API where you could force it to begin its response with e.g. `<svg` - it was a great way of forcing the model into certain output patterns.
They suggest structured outputs or system prompting as the alternative but I really liked the prefill method, it felt more reliable to me.
[1] https://github.com/ggml-org/llama.cpp/blob/master/grammars/R...
No one (approximately) outside of Anthropic knows since the chat template is applied on the API backend; we only known the shape of the API request. You can get a rough idea of what it might be like from the chat templates published for various open models, but the actual details are opaque.
But it takes lot of context as a experimental feature.
Use self-learning loop with hooks and claude.md to preserve memory.
I have shared plugin above of my setup. Try it.
A round drink coaster with a diameter of 9 sits between a beer glass and a wood table. The glass has a wall thickness of 1. What is the inner diameter of the glass?> Based on the information provided, it is impossible to determine the inner diameter of the glass.
Here is why:
The Coaster Dimension: Knowing the coaster has a diameter of 9 only tells us the size of the object under the glass. It does not mean the glass is the same size; the glass could be smaller (fitting entirely on the coaster) or larger (overhanging the coaster). The Glass Dimensions: While you provided the wall thickness (1), you did not provide the outer diameter of the glass. To find the inner diameter, the formula is: Inner Diameter = Outer Diameter - (2 × Wall Thickness)
Without knowing the Outer Diameter of the glass, the calculation cannot be completed.
> There isn’t enough information to determine the inner diameter *for sure*.
All we’re told is: - The coaster has a diameter of 9. - The glass sits on the coaster. - The glass wall thickness is 1.
Nothing explicitly states that the *outer diameter of the glass equals the coaster’s diameter*. The glass could be smaller than the coaster, which is very common.
*However*, if we make the usual implicit assumption in this kind of problem—that the coaster’s diameter matches the *outer diameter of the glass base*—then:
- Outer diameter of glass = 9 - Wall thickness = 1 on each side
So: \[ \text{Inner diameter} = 9 - 2(1) = 7 \]
*Inner diameter = 7 (same units as the coaster)*
Without that assumption, the problem is underdetermined.
```
Finding the Inner Diameter The coaster sits beneath the glass on the table, meaning the glass rests on top of it. Assuming the coaster matches the outer diameter of the glass base:
Outer diameter of glass = diameter of coaster = 9 Wall thickness = 1 (on each side, so subtract twice)
dinner=9−2(1)=7d_{\text{inner}} = 9 - 2(1) = 7dinner =9−2(1)=7 The inner diameter of the glass is 7.
```
Makes its assumption clear, seems reasonable?
A solar system has 3 planets in concentric orbit. PlanetZ is the farthest with an orbit diameter of 9. PlanetY has an obit diameter one greater than PlanetX. What is the orbit diameter of PlanetX?The inner diameter of the glass is *7*.
Here's the reasoning: - The coaster (diameter 9) sits between the glass and table, meaning the glass sits directly on the coaster - This means the *outer diameter of the glass equals the coaster diameter = 9* - The glass has a wall thickness of 1 on each side - *Inner diameter = Outer diameter - 2 × wall thickness* - Inner diameter = 9 - 2(1) = 9 - 2 = *7*
It does not make a single mistake, it identifies neologisms, hidden meaning, 7 distinct poetic phases, recurring themes, fragments/heteronyms, related authors. It has left me completely speechless.
Speechless. I am speechless.
Perhaps Opus 4.5 could do it too — I don't know because I needed the 1M context window for this.
I cannot put into words how shocked I am at this. I use LLMs daily, I code with agents, I am extremely bullish on AI and, still, I am shocked.
I have used my poetry and an analysis of it as a personal metric for how good models are. Gemini 2.5 pro was the first time a model could keep track of the breadth of the work without getting lost, but Opus 4.6 straight up does not get anything wrong and goes beyond that to identify things (key poems, key motifs, and many other things) that I would always have to kind of trick the models into producing. I would always feel like I was leading the models on. But this — this — this is unbelievable. Unbelievable. Insane.
This "key poem" thing is particularly surreal to me. Out of 900 poems, while analyzing the collection, it picked 12 "key poems, and I do agree that 11 of those would be on my 30-or-so "key poem list". What's amazing is that whenever I explicitly asked any model, to this date, to do it, they would get maybe 2 or 3, but mostly fail completely.
What is this sorcery?
“Speechless, shocked, unbelievable, insane, speechless”, etc.
Not a lot of real substance there.
Me too I was "Speechless, shocked, unbelievable, insane, speechless" the first time I sent Claude Code on a complicated 10-year code base which used outdated cross-toolchains and APIs. It obviously did not work anymore and had not been for a long time.
I saw the AI research the web and update the embedded toolchain, APIs to external weather services, etc... into a complete working new (WORKING!) code base in about 30 minutes.
Speechless, I was ...
When I last did it, 5.X thinking (can't remember which it was) had this terrible habit of code-switching between english and portuguese that made it sound like a robot (an agent to do things, rather than a human writing an essay), and it just didn't really "reason" effectively over the poems.
I can't explain it in any other way other than: "5.X thinking interprets this body of work in a way that is plausible, but I know, as the author, to be wrong; and I expect most people would also eventually find it to be wrong, as if it is being only very superficially looked at, or looked at by a high-schooler".
Gemini 3, at the time, was the worst of them, with some hallucinations, date mix ups (mixing poems from 2023 with poems from 2019), and overall just feeling quite lost and making very outlandish interpretations of the work. To be honest it sort of feels like Gemini hasn't been able to progress on this task since 2.5 pro (it has definitely improved on other things — I've recently switched to Gemini 3 on a product that was using 2.5 before)
Last time I did this test, Sonnet 4.5 was better than 5.X Thinking and Gemini 3 pro, but not exceedingly so. It's all so subjective, but the best I can say is it "felt like the analysis of the work I could agree with the most". I felt more seen and understood, if that makes sense (it is poetry, after all). Plus when I got each LLM to try to tell me everything it "knew" about me from the poems, Sonnet 4.5 got the most things right (though they were all very close).
Will bring back results soon.
Edit:
I (re-)tested:
- Gemini 3 (Pro)
- Gemini 3 (Flash)
- GPT 5.2
- Sonnet 4.5
Having seen Opus 4.5, they all seem very similar, and I can't really distinguish them in terms of depth and accuracy of analysis. They obviously have differences, especially stylistic ones, but, when compared with Opus 4.5 they're all on the same ballpark.
These models produce rather superficial analyses (when compared with Opus 4.5), missing out on several key things that Opus 4.5 got, such as specific and recurring neologisms and expressions, accurate connections to authors that serve as inspiration (Claude 4.5 gets them right, the other models get _close_, but not quite), and the meaning of some specific symbols in my poetry (Opus 4.5 identifies the symbols and the meaning; the other models identify most of the symbols, but fail to grasp the meaning sometimes).
Most of what these models say is true, but it really feels incomplete. Like half-truths or only a surface-level inquiry into truth.
As another example, Opus 4.5 identifies 7 distinct poetic phases, whereas Gemini 3 (Pro) identifies 4 which are technically correct, but miss out on key form and content transitions. When I look back, I personally agree with the 7 (maybe 6), but definitely not 4.
These models also clearly get some facts mixed up which Opus 4.5 did not (such as inferred timelines for some personal events). After having posted my comment to HN, I've been engaging with Opus4.5 and have managed to get it to also slip up on some dates, but not nearly as much as other models.
The other models also seem to produce shorter analyses, with a tendency to hyperfocus on some specific aspects of my poetry, missing a bunch of them.
--
To be fair, all of these models produce very good analyses which would take someone a lot of patience and probably weeks or months of work (which of course will never happen, it's a thought experiment).
It is entirely possible that the extremely simple prompt I used is just better with Claude Opus 4.5/4.6. But I will note that I have used very long and detailed prompts in the past with the other models and they've never really given me this level of....fidelity...about how I view my own work.