Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by actionfromafar on Monday November 09, 2026 @07:23AM
(#50424628)
Every hour baby-sitting a local model can be extremely expensive in billable hours.
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by techmunky on Monday November 09, 2026 @12:54PM
(#50428953)
Is there a model that doesn't need babysitting? Half my day is spent untangling BS that Claude and Codex hallucinate. Particularly around hallucinated product requirements. Its still faster than hand-writing code but only just. I'm seriously considering just going back to the early copilot days where I lead coding and just let it try to auto-correct. That was a great balance of AI enhancing my speed and workflows without removing any confidence in what was being shipped.
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by jatora on Monday November 09, 2026 @01:53PM
(#50429858)
give your models a more organized context/harness if they are hallucinating product requirements... and I'm not talking about some hulking context framework. just organize your documentation in a canonical way. This product requirements hallucination is something that would bite me constantly if...they ever actually hallucinated them (and they don't, ever). This is most certainly user error.
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by jesse_dot_id on Monday November 09, 2026 @05:45PM
(#50433377)
You're untangling hallucinated BS from Opus 5.5/Fable?
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by julianlam on Monday November 09, 2026 @02:07PM
(#50430100)
We are literally in this thread because so-called frontier SOTA Claude models are shitting the bed and require babysitting. So this argument is essentially moot.
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by whatarethembits on Monday November 09, 2026 @07:27AM
(#50424676)
What’s your local setup? I’d love to give it a spin; lack of 5 hours limits is much needed.
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by xeshuman on Monday November 09, 2026 @09:19AM
(#50426020)
Qwen 3.8 (and maybe soon 4) series models are probably the best right now for local AI. Specifically, for lower end hardware like 8gb GPUs you might find a lot of use in a Qwen 3.8 variant like Underdog Saluki 27B.
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by jmkni on Monday November 09, 2026 @07:29AM
(#50424694)
I might not need them but I'll sure as hell take them if they are available
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by enraged_camel on Monday November 09, 2026 @10:27AM
(#50426944)
>> But do people need the capabilities beyond what can be reasonably achieved with local models?
Yes? If you're building anything reasonably complex, it is a ton of work to keep everything in your head so that different parts of the system work seamlessly and work you do in one area does not adversely affect another area.
Re:Is Opus 5.5 nerfed? Thinking patterns changed on November 3
by jesse_dot_id on Monday November 09, 2026 @05:44PM
(#50433354)
How much did you spend on your local setup out of curiosity?
Also, yes, I do need the capabilities beyond what can be reasonably achieved with local models because threat actors are also using frontier models.
As for faster, maybe? It depends on the metrics and what you're doing with it. If you mean TPS, no, I get much higher TPS and even faster TTFT on my local setup than frontier models. If you mean time to complete tasks... maybe. If you're throwing whole projects at it to vibecode, yeah, a frontier model will dump slop so fast it'll make your head spin. If you're doing actual methodical development, like doing spec-driven development and actually reading the specs before spinning off agents to implement them, rather than just having another agent review it and yolo, you'll find that frontier models don't really push the needle that much, and you'll be making high-quality projects.