← Back to context Comment by matheusmoreira 4 months ago I hope local models advance to the point they can match Opus one day... 4 comments matheusmoreira Reply zozbot234 4 months ago If OP is correct, Opus has regressed to a point where local models are already on par with it. aveao 4 months ago Having tried GLM-5 and Minimax M2.5, alongside regularly using Opus 4.6 (on default thinking): Opus is still much, much better at writing non-garbage code. I haven't yet tried GLM-5.1 though. NinjaTrance 4 months ago Considering the advances in software and hardware, I would expect that in 2 or 3 years.And I hope we will eventually reach a point where models become "good enough" for certain tasks, and we won't have to replace them every 6 months.(That would be similar to the evolution of other technologies like personal computers and smartphones.) addandsubtract 4 months ago We said this since ChatGPT 3. People will never be content with local models.
zozbot234 4 months ago If OP is correct, Opus has regressed to a point where local models are already on par with it. aveao 4 months ago Having tried GLM-5 and Minimax M2.5, alongside regularly using Opus 4.6 (on default thinking): Opus is still much, much better at writing non-garbage code. I haven't yet tried GLM-5.1 though.
aveao 4 months ago Having tried GLM-5 and Minimax M2.5, alongside regularly using Opus 4.6 (on default thinking): Opus is still much, much better at writing non-garbage code. I haven't yet tried GLM-5.1 though.
NinjaTrance 4 months ago Considering the advances in software and hardware, I would expect that in 2 or 3 years.And I hope we will eventually reach a point where models become "good enough" for certain tasks, and we won't have to replace them every 6 months.(That would be similar to the evolution of other technologies like personal computers and smartphones.)
addandsubtract 4 months ago We said this since ChatGPT 3. People will never be content with local models.
If OP is correct, Opus has regressed to a point where local models are already on par with it.
Having tried GLM-5 and Minimax M2.5, alongside regularly using Opus 4.6 (on default thinking): Opus is still much, much better at writing non-garbage code. I haven't yet tried GLM-5.1 though.
Considering the advances in software and hardware, I would expect that in 2 or 3 years.
And I hope we will eventually reach a point where models become "good enough" for certain tasks, and we won't have to replace them every 6 months.
(That would be similar to the evolution of other technologies like personal computers and smartphones.)
We said this since ChatGPT 3. People will never be content with local models.