Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

You only need the frontier model for one single edit

stencil.so

Post reply on HN
Print view View original

21–30 of 107 posts

Re: You only need the frontier model for one single edit

#21

Post by carterschonwald »

canpan wrote: post #18
figmert wrote: post #15

The 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.

this so true. its really hard to make sure a model isnt going off the rails if i dont see full cot. the fact that oai and anthropic models hide it now has made them less reliable. which is a shame

Re: You only need the frontier model for one single edit

#22

Post by llbbdd »

danielciocirlan wrote: post #20
pqdbr wrote: post #17

Earlier quoted context omitted.

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”

I call him "my son"

Re: You only need the frontier model for one single edit

#24

Post by sgc »

wrs wrote: post #7

Lately 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'…

Actually it does include an important level of review. They say "init a TODO list with a validation step for each item", and then the last several sections of the execution are within the TODO - where it is validating the code.

To me that was the heart of the article and of what they did - create a self-validating todo list that deterministically forces the agents to stay on task, and then trim out just the right extraneous context (the actual planning) without messing with the read-file context which is where they found subagents burning most of their tokens.

Just a few days ago I was speculating about forking context to implement instead of spawning subagents here on hn. This is similar to that just several more steps more sophisticated. You could even fork the trimmed context here for very large tasks.

Re: You only need the frontier model for one single edit

#25

Post by trollbridge »

carterschonwald wrote: post #21
canpan wrote: post #18

Earlier quoted context omitted.

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.

this so true. its really hard to make sure a model isnt going off the rails if i dont see full cot. the fact that oai and anthropic models hide it now has made them less reliable. which is a shame

The great news is you can use DS-V-Pro, MiMo-V2.5-Pro, GLM-5.2, or K3 and see everything.

I tend to use 5.6-Sol now more for one shot type of tasks where all I want is the answer and I’m not going to read the reasoning.

Re: You only need the frontier model for one single edit

#26

Post by bensyverson »

wrs wrote: post #7

Lately 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'…

Yes, this is a core part of my workflow; use the smartest model (e.g. Fable) to generate a large hierarchical implementation plan, then clear the context and have a lesser model (e.g. Sonnet) track and execute the plan [0], often in parallel.

It all depends on how much work you're doing; if it's a simple task, there's virtually no need for plans at all; just have the smart agent do it. But if the work is going to take 5, 10 or 100 sessions, there's real value in the "smart agent plans, cheap agent executes" model.

[0]: https://github.com/bensyverson/jobs

Re: You only need the frontier model for one single edit

#27

Post by pphysch »

pixl97 wrote: post #19
pphysch wrote: post #13

> 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.

Do you think the average vibe coder or AI-smitten suit cares about slim code? A lot of folks still think "LOC = good" in 2026. It will be a hard sell for the practical engineer.

Even if they understand "slim code = fewer tokens = less spend" they still have to grok that less code is not less functionality.

Re: You only need the frontier model for one single edit

#28

Post by ricardobeat »

I just did this five minutes ago. Started a task with Kimi K3, noticed cost going up, switched to Minimax M3 continuing from the same context. Really easy to do with Crush/OpenCode.

It works quite well most of the time. For very deeply technical tasks, where exploration involves multiple agents (and blowing up context limits a few times), I'll have a plan written down to disk that will be much longer than 2k tokens.

Re: You only need the frontier model for one single edit

#29

Post by ricardobeat »

bensyverson wrote: post #26
wrs wrote: post #7

Lately 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'…

Yes, this is a core part of my workflow; use the smartest model (e.g. Fable) to generate a large hierarchical implementation plan, then clear the context and have a lesser model (e.g. Sonnet) track and execute the plan [0], often in parallel. It all depends on how much work you're doing; if it's a simple task, there's virtually no need for plans at all; just have the smart agent do it. But if the work is going to tak…

This is exactly what the post argues against though, as it leads to higher overall cost.
Post reply on HN