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
The new rules of context engineering for Claude 5 generation models
31–40 of 434 posts
Re: The new rules of context engineering for Claude 5 generation models
#32> Now: Auto-memory
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.
A big reason I use LLMs is because I can try out wild ideas and then just throw it away. I don't want those to pollute the context.
Re: The new rules of context engineering for Claude 5 generation models
#33We 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...
My current thinking -- what I've been thinking about a lot yesterday and today -- is not encoding the exact requirements into the prompt and context but rather focus on the verifier and roll back if needed. There are of places in computer science where non-deterministic behavior is optimized. For example, UDP packets which are just ignored and speculative execution in modern CPUs guesses which branch a program will take and rolls back when wrong.
Ideally, a cheap verifier checks that the exact requirements are satisfied, rolling back and updating the prompt for another iteration if they aren't. If ten iterations with ten verifications steps at the end of each before the exact requirements are met costs less or in less time than a developer who can accomplish it in one attempt, it is still better.
Re: The new rules of context engineering for Claude 5 generation models
#34We 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...
We could write instructions like literature. Maybe we could call it "Literate Programming"?
Re: The new rules of context engineering for Claude 5 generation models
#35so yeah we should pretty much do as we would with a junior team member:
- we should try to give good non self contradicting guidance
- we should expect the team member to have knowledge of the craft
- we should focus on higher level, taste and preferences
Re: The new rules of context engineering for Claude 5 generation models
#36Is 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.
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.
Re: The new rules of context engineering for Claude 5 generation models
#37This 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 mu…
I have a document generation task that I used to run with 4.8. This morning after it switched to 5, the documents were consistently 30%-40% longer for the same prompt... Not evaluated whether they are actually better or worse yet, but what was interesting was how consistently more verbose it was.
Re: The new rules of context engineering for Claude 5 generation models
#38We 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...
then we can make a frame for it to work
I've always loved things that grow. Maybe we should name the first frame for work Primavera.
Re: The new rules of context engineering for Claude 5 generation models
#39We 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...
maybe we should all get specially, local working versions so that when we build our software they're not broken by the whims of multibillion dollar corporations.
Re: The new rules of context engineering for Claude 5 generation models
#40tl;dr: use the new `claude doctor` command to simplify the context you give your Claude models to make sure that you're getting the best results.