The new rules of context engineering for Claude 5 generation models
by mellosouls on 7/25/2026, 8:42:35 PM
https://claude.com/blog/the-new-rules-of-context-engineering-for-claude-5-generation-models
Comments
by: mycentstoo
We should design a specific language to make sure that we can encode the exact requirements that we want. Something that has a limited set of keywords that are explicit. Wait a minute...
7/25/2026, 9:46:11 PM
by: firasd
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.<p>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.<p>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<p>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.
7/25/2026, 9:40:19 PM
by: Fordec
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.<p>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.
7/25/2026, 9:48:30 PM
by: m3h
Is there a specific list of changes they made to the system prompt? They're claiming they removed 80% of it. That's quite substantial. It would be good to know what the model knows to do by training and what we need to avoid over-specifying in our system prompts.<p>Saying that "give Claude judgment" is too vague for agent implementors. Given the lack of specific details, my takeaway is that we need to go and review all context and rework prompts from prompts/descriptions from scratch until they pass the evals again.
7/25/2026, 10:26:39 PM
by: guybedo
so yeah we should pretty much do as we would with a junior team member:<p>- we should try to give good non self contradicting guidance<p>- we should expect the team member to have knowledge of the craft<p>- we should focus on higher level, taste and preferences
7/25/2026, 10:25:48 PM
by: 0gs
crazy to me that this starts with "I've written previously" yet continues the zero human attribution (that i could find?) trend in frontier model blog posts
7/25/2026, 10:20:57 PM
by: janpeuker
The point about not using examples is important, I recently noticed with the new "eagerness" of models it constraints them too much, so I use counter-examples. Recently I've switched to "think about the existing biases and assumptions in the design and try to exploit them, for example why do we X not Y".
7/25/2026, 10:11:09 PM
by: simonw
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.
7/25/2026, 9:44:22 PM
by: Kiro
> Now: Auto-memory<p>Not Claude Code but I just had a task where it started referring another conversation that was complete nonsense and throwaway. I absolutely don't want things to get added to some memory behind my back.<p>A big reason I use LLMs is because I can try out wild ideas, even implementing a robust production-ready prototype, and then just throw it away. I don't want those to pollute the context.
7/25/2026, 10:21:29 PM
by: npstr
The bitter lesson.
7/25/2026, 9:45:14 PM
by: luciana1u
the natural endpoint of this trend is a system prompt that just says "you know what to do" and the model actually does
7/25/2026, 9:37:47 PM
by:
7/25/2026, 9:59:33 PM
by: onesandofgrain
This is obvious and a meaningless article by claude. The system prompt isnt a fixed ruleset and never has been
7/25/2026, 9:46:59 PM