WPDevelopers

@AstraiaAI Trillions, but I only have a 50 token context window

How many parameters are there in the human brain?

@bentossell @Mappletons 😁

@thewpdevs @Mappletons that’s my son

Inexplicably down a rabbit hole getting agents to craft me some beautiful poppies, but this is where "hey claude attach these variables to sliders" works a charm

@bentossell @Mappletons Claude?

@Mappletons my daughters name ❤️

@marcelpociot At first it blew me away, but it’s been doing some questionable shit and my trust has dropped. It merged and deployed an early stage PoC to prod in an earnest pursuit of setting up integrations itself. It’s been relegated to auditing only for now.

Alright, I think GPT 5.6 quickly became my favorite model. Fable is great, but I feel like GPT 5.6 just gets more things done in a higher quality output What's your verdict?

@kimmonismus so weird - I had this issue a week before 5.6 dropped. burned through 2 resets and $200 usage credits which is obscene for me. But in the last week it's been impossible to make a dent in usage limits (and I'm trying!)

Seriously, this has to stop. I've now set GPT-5.6 from high to medium (not fast mode, of course), and I'm still burning through my rates at an insane rate. My 5 hours are almost gone -again. I've already used up all three resets. OpenAI needs to work on its efficiency. This is the biggest bottleneck.

@theo I’ve been rerouted (fairly silently - the model picker just changed to Opus - no notice/alert) first time on a test suite review task.

Fable 5 has yet to reroute me for any real code work. The concerns were massively overblown.

@AlexStandiford @sirenaffiliates Looks interesting! We currently use AffWP extensively, but will keep an eye on this. Very best of luck!

Welp, @sirenaffiliates is officially on the dot org repo! wordpress.org/plugins/siren-…

@robinebers Solution: use Opus 3 for a week - it’s still available! Every current model will feel like a dream after 🤣

where the fuck is Fable 5? I can't take this shit anymore every model feels so dumb in comparison

@robinebers just have a niggling feeling that yes it's coming back, but it'll be nerfed

at this point i'm just manifesting 🙏🏻 ✨

@jordankdalton YES!

Just me, or is claude "slow" today? Simple context is taking multiple minutes despite low token counts.

@robinebers same. burned an ungodly amount of tokens. so productive. really interesting how this plays out. Was this just spite on the part of US Dept of War from convos a few months ago? Do OpenAI release a monster model now? Would they get the same treatment? Does Opus get secretly better?

missing Fable 5 so much not even talking about coding it was just so much smarter at ingesting data, writing files, and connecting things Opus is ok at these things (honestly, much better than GPT-5.5), but Fable was on another level while it was around, I've processed 15+ hours of video, YouTube competitors, screen frames and thumbnails, patterns and anti-patterns it was the first model that really made me feel like I can trust it with knowing what I want, how to store it reliably the more I analyze the work that this model has produced for me, the more I realize that Fable was the first model that has a better understanding of how AI works and that resulted in it creating files and prompts that are dramatically better than anything any other model would produce hope it comes back soon because it feels like we went backwards bad

@andyhennie @robinebers Hmm it does for me too. Didn’t configure anything - just saw threads in app that I had initially started in CLI. A double take moment as it was unexpected!

@robinebers Doesn’t for me. Heavy CLI user. It just do it automatically on your computer, wo you having to do anything?

Codex is giving up on me after almost 4 days of /goal it can't handle the chat history anymore and it gets stuck here forever CLI keeps freezing, too obviously pushing the envelop here significantly but would be nice to future-proof this bummer, I really wanted to see how far I can push the /goal feature 😂

@robinebers +1!!

In Codex, I wish there was a model selector before you accept a plan. feels like planning with High/Extra High and implementing with Medium is pretty common

Ironically, this is the first hidden backdoor I found while intentionally hunting for bad actors in the WordPress plugin repo. It might also be my last big find. With AI, bad actors won't be able to hide for long. anchor.host/a-sold-wordpre…

Claude Opus 4.6... you're killing me today.

@robinebers yeah was getting obscene Opus stupidity last week... seems to have sorted itself out this week though. Codex yesterday had an hour of nonsense too...

when I say Claude Opus 4.6 is behind, that's what I mean this model is truly the laziest of the bunch Codex would never

@stevemarkperry 😅 what model out of interest? I was having a lot of moments like these with Opus 4.6 last week, but it's much better this week

By this time, AI will be writing all the code. Erm, I don't think so. Not with crap like this. Back around sunshine.

@rootswp FYI: I wanted to look into Radicle a bit and noticed the link to the docs is returning a 404

✨Acorn v6 has been released with Laravel v13 support PHP 8.3 is also now the minimum requirement Sage and Radicle have both been updated with Acorn v6 roots.io/acorn-v6-relea…

@nickarceco It literally just crashed as I scrolled down a bit

This is the future of website design that I'm scared of respira.press What am I supposed to look at? what even is this?

@mitchellh So… where’s the waitlist? 🙂

I’ve been forcing myself to use the GUI agent apps the past week just to learn. One week isn’t enough experience yet, but I think they all miss the mark (so far) and I’m deeply fighting the urge to do one with my own taste. I’m not gonna do it. I’m not gonna do it.