Software Engineer Founder of the vibecoded metaverse @SlopCityGame https://teapawt.net/t.co/COu27NG5zr
Joined April 2026
- Tweets212
- Following162
- Followers51
- Likes61
Pinned Tweet
I've spent the past two weeks cooking up Slop City. It's been a pretty wild fortnight.
It's a mix of the cosy games I love and what I hoped my ideal RPG game would become. I've wanted to build a social world like this for years, and I'd love for vibecoders to make it their hangout.
Frontier models made this possible, especially the 3D work. The name is a nod to how it started, but I want to make something polished that people keep coming back to.
Really excited to see what this becomes!
1/8 Slop City has grown since our last update. Farming, home customisation, five new homes, swimming and Casino Nightlife are here. It's a free 3D social game you can play in your browser. Join here: slopcity.fun
If you ship real projects in your side-time, you're building games, tools, and things people actually use. Everyone else is configuring their second brain for the third time this month.
Funnily enough, that's why I also built my own AI-powered second brain to do the work for me😂
I still don't quite believe these 'one improvement a day' posts are actually going to be anything substantial to bring back people who have recently left the Codex ecosystem... i mean, even with this 'upgrade', Opus 5.5 is still winning at a rate of 69 TPS
Try again tomorrow @thsottiaux
How to vibe code a game:
As a solo dev and AI tinkerer I've shipped and scrapped a lot of side projects. Most go nowhere.
Some actually stick. I've slowly found a workflow that my builder friends now ask about.
AI has actually made me more productive. It's inspired me to open up my editor and ship that feature, or start that side project. Because no matter how rough it is, at least it's something I'VE built, and tbh I'm shipping more now than I ever had motivation to before.
Trailer made with Opus 5.5 🫡
The Slop City trailer is here. 🌞
A little online town to make yourself at home. Spend the evening at the casino or find a quiet spot to fish.
Free to play in your browser.
Where are you heading first?
slopcity.fun
Building my game Slop City has me thinking about what actually makes a hangout game popular. Cosy mechanics, low friction logins, a reason to come back tomorrow. What keeps you logging into a social game past week one?
In other news, I've been busy at work testing the new sonnet 5.5. It's a pretty cool model
I had a heart scan recently, so I decided to build a simulation of one to learn how they worked. One hour later and got this.
You can test it here: claude.ai/artifact/Sc6y7z5jC…
@Rizz3D this one's for you
For those interested, here's how I use Claude currently, with all of my subagent profiles.
@aSam_7878 you mentioned to let you know when I have a solution to my usage limit problem... this has significantly improved it! The above project used 5% of my 5-hour limit (about 2% of my weekly).
I think the trick is to stick to `high` effort at the maximum, and switch some of my subagents to sonnet depending on their use-case. Only the debugger using xhigh.
This is probably the most upset i've felt about an OpenAI launch. In my books they've been great up until this point. It's a real shame to see them burn bridges like this
I have no interest in making 6.1 sol my daily driver seeing the comparisons between that and Sonnet 5.5. I'm sticking to Anthropic, and if my usage limits are visibly worse with Astra, then i'm leaving the OpenAI ecosystem for a while
Beyond a joke
DevDay is a massive L for me:
$500 plan being only a tiny bit better than the OLD $200 plan at over double the price
$200 plan being nerfed, with a subsidised model (gpt 6.1 Sol) to make people feel less bad that the plans are being nerfed
Ultrafast being a whopping $60/$300
And the icing on the cake...
*cuts usage by a half on the $200 plan*
"It's going to be better for everyone... (that uses Sol)"
Listen buddy, no one is using Sol 🤪
It's so over
I’ll explain the new Pro 200 plan differently, before I start live tweeting from DevDay on things that are going out!
Today we are going to ship a number of things that increase what you can do across the Plus and Pro plans. A lot of compute is online for this increase. As we increase the floor, we are changing the relative difference between plans to be
Plus = 1X
Pro 100 = 5X
Pro 200 = 10X
and we are reopening subscriptions for Pro 200 (we had paused it). If you have an existing plan you will keep the 20X multiplier for a bit and also receive a lot of additional credits because we know changes are hard even if it means that everyone will get more in the end.
Happy DevDay all - sadly not off to a great start it seems...
Am I the only one seeing this as a nerf? I don't understand how making models more efficient (probably also meaning quality is compromised) means they can scale down the plan to suit, thus getting "less usage" but because it's cheaper, it's "the same usage".
Why not just keep the plan as is and let us reap the extra benefit?
Hi,
Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan.
Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago.
(a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want.
(b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions.
(c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent.
(d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet.
I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news.
Codexingly,
Tibo
Nothing else needs to be said
UPDATE: Not quite "shambles" but "annoyed" (lol) by the release of Opus 5.5 and seeing its successes, OpenAI have internally fast tracked not only GPT 6.1 Astra but what they call the first true AGI, code named 'Bel'
It is widely believed that Bel far exceeds Fable 5.5 which was scheduled for release in 2~3 weeks and that no frontier labs can currently match it.
The second wave of OpenAI's attack is the new jalapeno chips which will enable 750t/s from Sol/Astra models on ultrafast mode for the $500~$600/month Pro Max plan.
Contrary to what everyone prematurely concluded, it appears Pro Max focuses not only on usage but ultrafast inference (think /fast but speed is 8~10x)
I am holding off on any decisions until I see OpenAI's response to Fable 5.5 release in the coming weeks. Ball is now in Anthropic's court, if they release Fable 5.5 too early they risk getting mogged by not only Bel but jalapeno ultrafast. They can't sit on it for too long either because Gemini 4 Pro are expected to be between Opus 5.5 and Fable 5.5.
Situation is tense in Anthropic even after a brief victory and social media blitz. OpenAI's quiet confidence has frightened them. We may be seeing OpenAI pull away from the pack in both inference and compute.
It is very likely that OpenAI will use this gap created by Bel to launch its end game before its giant IPO next year, the coveted RSI model for large government/enterprise.