[HN Gopher] Selection rather than prediction
___________________________________________________________________
Selection rather than prediction
Author : languid-photic
Score : 18 points
Date : 2026-02-03 23:31 UTC (3 days ago)
(HTM) web link (voratiq.com)
(TXT) w3m dump (voratiq.com)
| tomtom1337 wrote:
| Any suggestions for <<orchestrating>> this type of experiment?
|
| And how does one compare the results in a way that is easy to
| parse? 7 models producing 1 PR each is one way, but it doesn't
| feel very easy to compare such.
| jmalicki wrote:
| Is this going to get my Claude subscription cancelled if I run it
| with a claude backend, given that it's orchestrating the CLI? I
| am still a little unclear about the boundaries of that.
| fph wrote:
| AI is like XML: if it doesn't solve your problem, you are not
| using enough of it.
| bisonbear wrote:
| Intuitively makes sense, but in my experience, a more realistic
| workflow is using the main agent to sub-agent delegation pattern
| instead of straight 7x-ing token costs.
|
| By delegating to sub agents (eg for brainstorming or review), you
| can break out of local maxima while not using quite as many more
| tokens.
|
| Additionally, when doing any sort of complex task, I do research
| -> plan -> implement -> review, clearing context after each
| stage. In that case, would I want to make 7x research docs, 7x
| plans, etc.? probably not. Instead, a more prudent use of tokens
| might be to have Claude do research+planning, and have Codex do a
| review of that plan prior to implementation.
| girvo wrote:
| > straight 7x-ing token costs
|
| You are probably right, but my work pays for as many tokens as
| I want, which opens up a bunch of tactics that otherwise would
| be untenable.
|
| I stick with sub-agent approaches outside of work for this
| reason though, which is more than fair a point
___________________________________________________________________
(page generated 2026-02-07 23:00 UTC)