Does anyone have a name for that really neat "the bar chart is a bookshelf, you can hover a spine to see the cover" vis? I've never seen it before.
You only need the frontier model for one single edit
11–20 of 107 posts
Re: You only need the frontier model for one single edit
#12This is a lot of words to say "switch models instead of writing a plan file and starting a new session" which I do anyway.
That said, it takes me a while to reads plans and often I'll take a break, by when the cache has expired. At that point it may be better to start over
Re: You only need the frontier model for one single edit
#13> Any agent, any model, any scaffold: the bill is essentially O(reads)
Therefore token sellers have incentive to produce verbose, unreadable code
Re: You only need the frontier model for one single edit
#14This is a lot of words to say "switch models instead of writing a plan file and starting a new session" which I do anyway. That said, it takes me a while to reads plans and often I'll take a break, by when the cache has expired. At that point it may be better to start over
I don't think that is the takeaway at all.
Re: You only need the frontier model for one single edit
#15The reason I use plan then implement is because I can adjust the plan, whereas if I get it to implement straight away, it might (and often does) make the wrong decisions that will be harder to adjust, or I'd have to adjust it after the fact.
Re: You only need the frontier model for one single edit
#16This entire argument rests upon the fact that Gemini Flash ain't cheap.
Try plan with opus 4.8 and then implement with Deepseek v4 flash - its 35x cheaper for reads, 90x cheaper writes, and 18x cheaper cache reads.
Or plan with Deepseek Pro, or even Flash itself. I've been impressed with both.
Re: You only need the frontier model for one single edit
#17Lately I'm trying a variation on this: Have the main agent make a phased implementation plan, then for each phase, have it start an implementation subagent with a focused prompt, then review that agent's work in the main session. The theory being that the main session still contains all the research, but it can review just the diff rather than have the entire implementation session in context as well. The post doesn'…
I’m using Claude code dynamic workflow like this. I tell Fable to use a workflow. He is the planner, orchestrator and reviewer. Opus agents are implementers. Works unbelievably well.
Re: You only need the frontier model for one single edit
#18The reason I use plan then implement is because I can adjust the plan, whereas if I get it to implement straight away, it might (and often does) make the wrong decisions that will be harder to adjust, or I'd have to adjust it after the fact.
One big pain point is not seeing the thinking trace. I noticed using pi with a self hosted model that I could spot, stop and correct my prompt much faster. With claude etc I have to first wait for it to think 3 minutes and then notice it got completely off the path I wanted.
I still use a plan, because my local model is not as smart as opus, but I can iterate much faster.
Re: You only need the frontier model for one single edit
#19> Any agent, any model, any scaffold: the bill is essentially O(reads) Therefore token sellers have incentive to produce verbose, unreadable code
Whichever token seller defects can capture a larger chunk of the market with slimmer code.
Re: You only need the frontier model for one single edit
#20Lately I'm trying a variation on this: Have the main agent make a phased implementation plan, then for each phase, have it start an implementation subagent with a focused prompt, then review that agent's work in the main session. The theory being that the main session still contains all the research, but it can review just the diff rather than have the entire implementation session in context as well. The post doesn'…
I’m using Claude code dynamic workflow like this. I tell Fable to use a workflow. He is the planner, orchestrator and reviewer. Opus agents are implementers. Works unbelievably well.
“He”