I set claude about writing docstrings on a handful of files - 4/5 files couple 100 lines each - couple of classes in each - it didnt need to scan codebase (much).
Low danger task so I let it do as it pleased - 30 minutes and was maxed out. Could probably have reduced context with a /clear after every file but then I would have to participate.
You can tell it to review and edit each file within a Task/subagent and can even say to run them in parallel and it will use a separate context for each file without having to clear them manually
I haven’t ran any experiments about token usage with tasks, but if you ran them all together without tasks, then each files full operation _should_ be contributing as cached tokens for each subsequent request. But if you use a task then only the summary returned from that task would contribute to the cached tokens. From my understanding it actually might save you usage rates (depending on what else it’s doing within the task itself).
I usually use Tasks for running tests, code generation, summarizing code flows, and performing web searches on docs and summarizing the necessary parts I need for later operations.
Running them in parallel is nice if you want to document code flows and have each task focus on a higher level grouping, that way each task is hyper focused on its own domain and they all run together so you don’t have to wait as long, for example:
If I understand correctly, looking at API pricing for Sonnet, output tokens are 5 times more expensive than input tokens.
So, if rate limits are based on an overall token cost, it is likely that one will hit them first if CC reads a few files and writes a lot of text as output (comments/documentation) rather than if it analyzes a large codebase and then makes a few edits in code.
That is indeed exactly what the article says — I’m not certain GP is right on this.
Kenji’s original tests seem to confound this as well: every 2.5min of slicing produces steadily less juice, despite the fact that the steak’s internal temp should be rising for some of that time.
“Internal” temperatures are measured near a single point. Some internal, watery, parts will be hotter than other internal, watery, parts. On average, the temperature goes down over time even if it increases in some local parts.
So the average pressure will decrease.
(Yes, for an ideal cavity, pressure is equal everywhere, but for meat which contains highly tortured paths and a three-phase state mixture for the vapors to escape from - there can be different pressures in different areas especially once there’s any flow at all)
In what ways is that better for you than using eg Claude? Aren’t you then just “locked in” to having a cloud provider which offers those models cheaply?
Two can run Claude, AWS and Anthropic. Claude rollout on AWS is pretty good, but they do some weird stuff in estimating your quota usage thru your max_tokens parameter.
I trust AWS, but we also pay big bucks to them and have a reason to trust them.
I'm astonished at the stickiness of chatgpt though. It's clearly not the best platform/model but all my none tech friends just equate LLMs = ChatGPT (4o as well).
It just benefitted from the Kleenex/Google effect due to being the first real mainstream breakthrough of GPT tech among average users ("normies").
I expect, whether OpenAI is even still around in 15+ years or not, that my grandparents will continue telling me about "that ChatGPT" well into the future.
o3/o3-pro is probably the best model, or very close to being the best model, overall. It beats Grok 4 in writing/composition and analysis tasks. [1] Performance is a toss-up between o3 and Claude 4 Opus, but I find o3 easier to interact with and more trustworthy. (Less likely to push back against requests and more likely to attempt to fulfill them in good faith.)
4.5 is also great for certain things. Of all models, it's the second best writer. (DeepSeek R1 is the best prose stylist, surprisingly!)
A really effective prompt is created by developing an accurate “mental model” of the model, understanding what tools it does and doesn’t have access to, what gives it effective direction and what leads it astray
