Re:SlopCodeBench 10/2026 – Opus 5.5, Astra wins overall, xhi...
by elcritch on Tuesday October 20, 2026 @08:58PM
(#50174786)
I hate to be pedantic, but LARP stands for live action role playing.
Only mentioning it because LLMs are already taking over software development and everything online. Let's keep them out of our meet space peculiarities (1) while we can. ;)
Re:SlopCodeBench 10/2026 – Opus 5.5, Astra wins overall, xhi...
by disgruntledphd2 on Wednesday October 21, 2026 @03:49AM
(#50177373)
Yeah, they're clearly table top roleplayers.
The real question is are they white wolf or DnD?
Re:SlopCodeBench 10/2026 – Opus 5.5, Astra wins overall, xhi...
by watercolorblind on Wednesday October 21, 2026 @06:20AM
(#50178513)
I'd say shadowrun.
Re:SlopCodeBench 10/2026 – Opus 5.5, Astra wins overall, xhi...
by 10111001 on Wednesday October 21, 2026 @09:41AM
(#50180811)
> I hate to be pedantic, but LARP stands for live action role playing.
> Only mentioning it because LLMs are already taking over software development and everything online.
In our glorious future, you'll have your agent LARP for you with your friends' agents, so you all can spend more time doing more fulfilling tasks like watching ads on Instagram.
Re:SlopCodeBench 10/2026 – Opus 5.5, Astra wins overall, xhi...
by mrheosuper on Tuesday October 20, 2026 @11:52PM
(#50175893)
Why stop at "You are a senior partner at a prestigious law firm that focuses on reading licensing contracts..." why not "You are super programmer/developer that has been programming with Ada using punchcard, having Linus on quick dial, you can smell BS code from miles away and know exactly which question to ask".
Re:SlopCodeBench 10/2026 – Opus 5.5, Astra wins overall, xhi...
by CharlieDigital on Wednesday October 21, 2026 @07:26AM
(#50179084)
Eval it and see.
You might be surprised.
(But also, this is more or less what I do with Paseo profiles)
Distinguished Member of Technical Staff, for example, is asked to "expand the solution space" which I find has a strong effect on approaches considered (it doesn't know what was already considered on the main thread; only the domain and problem space).
This also helps with context growth since the sub-agents do the heavy lifting (e.g. search, read docs) and just provide the key bits back to the lead.
Like you, I was a single-model, single-TUI user up until three weeks ago when I picked up Paseo and it is the only tool that I've found that has significantly positively improved my throughput without sacrificing quality of product.
Is it "larping"? I ran an eval today on a contract ingest and extract agent I'm working on. Changing the <role> fragment of the prompt lifted the results by +7 points by simply changing the text to the effect of "You are a senior partner at a prestigious law firm that focuses on reading licensing contracts..." and some bits about the content the agent is reviewing + objective. No one would believe it without an eval.
Claude docs explicitly say to LARP[0]:
My conclusion: the agents like to LARP so I'm happy to LARP with them.[0] https://platform.claude.com/docs/en/build-with-claude/prompt...