Gpt and AI Discussions

Message

#211 Post by **ViperDiscord** » Mon Apr 13, 2026 5:10 pm

Dont you have gpt or opus?

#212 Post by **ViperDiscord** » Mon Apr 13, 2026 5:12 pm

both, gpt 5.4 includes codex 5.3.

Yes there have been reports of claude degradation.

I have gpt plus $20/mo but they seem to have really lowered the tokens for plus accounts.
I have claude Max 5x

#213 Post by **ViperDiscord** » Mon Apr 13, 2026 5:12 pm

Im sad nanogpt took GLM 5.1 and Qwen 3.6 out of subscription

#214 Post by **ViperDiscord** » Mon Apr 13, 2026 5:13 pm

I actually bought a service that Gave me 500M tokens (70$) forOpus 4.6/GPT 5.4 and Im about 2 weeks i used 360M tokens xD they Run out só fast

#215 Post by **ViperDiscord** » Mon Apr 13, 2026 5:14 pm

Trying to create a Dijkstra algorithm and background input for a bot for Maplestory

#216 Post by **ViperDiscord** » Mon Apr 13, 2026 5:21 pm

how was GLM 5.1 when you used it?

#217 Post by **ViperDiscord** » Mon Apr 13, 2026 5:26 pm

It was good, not as good as opus on its prime ofc, would maybe be similar now that opus hás downgraded

#218 Post by **ViperDiscord** » Mon Apr 13, 2026 5:29 pm

Qwen 3.6 surprised me most though almost 1 shotting A* algorithm

#219 Post by **ViperDiscord** » Mon Apr 13, 2026 5:29 pm

I am currently working on a FabricMC style modloader for a java mmo.
My prototype worked great, now working on the tooling so remapping all the ProGuard names from SLK4D23JF (class method field) names can be mapped to intermediary names with a tool to will reapply intermediary names based on bytecode analysis when the game updates and all the proguard names change. I mapped all the classes to human readable names already, got a couple 1000 method and fields renamed. This is going to be a huge token burner.

#220 Post by **ViperDiscord** » Mon Apr 13, 2026 6:27 pm

If you aren't setting your Effort level and/or have adaptive thinking enabled, then ya, you'll get mixed results.

#221 Post by **ViperDiscord** » Mon Apr 13, 2026 6:28 pm

Effort level is at maximum all the time

#222 Post by **ViperDiscord** » Tue Apr 14, 2026 12:10 am

though GPT 5.4 is alot slower, it solved almost all problems in 3 small prompts

#223 Post by **ViperDiscord** » Tue Apr 14, 2026 12:10 am

(everything else was basically opus 4.6 thinking on max effort)

#224 Post by **ViperDiscord** » Tue Apr 14, 2026 4:26 am

When a new model comes out, its settings are always on high internally.. then after a week or 2 they see how much people are using it and how much resources its taking up.. to basically tune it to fit their current servers.. This is where it seems like they downgrade it. Personally IMO.. I think they also turn the current model down just before a new model is released.. so it makes the jump seem a lot bigger than it is.

#225 Post by **ViperDiscord** » Tue Apr 14, 2026 4:39 am

Yea, that seems to be the trend

Gpt and AI Discussions

Saringeti Wrote:

Mysticdrew Wrote:

Saringeti Wrote:

Saringeti Wrote:

Saringeti Wrote:

Mysticdrew Wrote:

Saringeti Wrote:

Saringeti Wrote:

Mysticdrew Wrote:

swiftraccoon Wrote:

Saringeti Wrote:

Saringeti Wrote:

Saringeti Wrote:

PitViper Wrote:

Mysticdrew Wrote: