The New Rules of Context Engineering for Claude 5 Generation Models

I've always thought that extensive throat-clearing and prefixing the Treaties of Westphalia-length instructions into the context window was unnecessarily baroque when you can just talk to the agent.

I guess part of it is also that I don't mind doing 'hand-edits' like for example LLMs love to say "// so and so removed" I just go and remove that manually later rather than being like "don't comment about what you removed!11" cause you're really fighting deep grooves in the model's behavior at that point.

But I also have a hands-on human-in-the-loop working style so I guess maybe for people who just want to say "implement all open features in github issues" and walk away maybe there needs to be more of all this CLAUDE.md stuff

However I suspect there was always some gearhead type attraction to setting up detailed harness configs that may be unnecessary and more like hobbyist tinkering.

They are imo over-relying on Claude automemory here, which is terrible at contextualizing memory access and makes huge leaps that don’t make sense - except when it’s actually useful, which makes the problem even worse for an operator who can’t see the thinking process anymore.

Yes, I worked on a related project, no I don’t want you to use those memories to make assumptions which emerge as decisions that I didn’t want. With reasoning traces hidden, I am sometimes not even sure if it used those memories or just independently decided that PCI-DSS subsection-whatever is somehow relevant to this PR that has the word “credit”.

There is no way for me to fully configure memory preferences at a granularity which would be useful, and so I continue to use context files (and other tools, sometimes) to ensure the right memories are stored and surfaced at the right times.

There’s a lot of room for agent memory improvement across the ecosystem, and I don’t think the LLM providers should try to own this vertical slice. This will never happen though, because it makes us “sticky”.

Or maybe I’m holding it wrong.

This all strikes me as an effort to move tailoring the harness out of the easily transferable .md file into specific Anthropic tooling to increase lock in.

I've been running Opus 5 today and it's already done accidental deletions, made far more mistakes and worked around deliberate hook controls than previous Opus versions combined. Also it looks like token usage is up as it fails at the task the first time around much more frequently than 4.8.

We want more control, not less.

This (among many others) is the reason I use GPT over Claude. It adheres very closely to your instructions and rules. You can build up your own workflows and systems as a result.

Claude just does whatever it wants, regardless of what you tell it. It's a miserable experience.

Claude is what you use when you want to one-shot a simple cookie-cutter product that has no nuance in it. A product that everyone else is going to develop as well.

ChatGPT is what you use when you want bespoke products and steerability over complex codebases with nuanced decision making.

Anthropic are optimizing for the person who has never written a line of code in their life and has no idea what they want. Computer go brrrr. OpenAI are optimizing for software developers who want to take a systems based approach.

I wonder whether this applies more to coding agents, or whether it'll apply as well to other types of agents.

It feels like coding agents get better at a faster rate and are easier to train.

I've been prompting Fable 5 to "use your own judgement" with respect to things like tests recently (based on earlier tips from Thariq) and it seems to work well, which is entertaining since apparently now "judgement" is a characteristic of a model that we need to care about.

Most of this article seems like... common sense? Not sure how it's related to the latest generation in particular. I usually find Anthropic's advice on how to prompt their own models deviating from what I see in practice, which is puzzling. Their system prompt was always way too bloated and they kept it as a huge piece for some reason, instead of breaking up into parts. Shouldn't they know better? I wonder if they looked at Pi performing great with minimal amount of distractors in the context and cut their prompt down too, pretending they found something new in their recent models.

> Earlier Claude models could sometimes need repeated instructions or be more likely to listen to instructions at the end of their context window than at the start.

This seems to imply they solved serial position biases like lost-in-the-middle and recency/primacy? Sounds dubious. Labs started claiming this early 2025 and some benchmarks agree, but every time I run an eval on real use cases it's clearly there, especially at longer contexts.