sayso (@akaSAYSO) header
sayso (@akaSAYSO) profile picture

i built a museum to hang my own art @ https://teapaw.org/t.co/0Yu1Hxamj0 🖼️ you can wear my art on your heart @ https://teapaw.org/t.co/DAgMeRXsHB ❤️

Melbourne + Tokyo
Joined May 2015
Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)Photo by sayso (@akaSAYSO)
Pinned Tweet
i built MOSA: a museum website to hang my own art 🤭 inside it looks like a slider/carousel but every art piece is a new webpage that looks/feels/loads like slider (thanks to @astrodotbuild, @Cloudflare 🙏🏽❤️) is a wip — pls reply with bugs/improvements sayso.co/
1
5
429
Delete a chat in Agentaus and it's permanently deleted. Not archived. Not kept for training. Just gone.
We built Australia’s own AI model, and today it’s open to the world. Agentaus 1 (@AgentausTD): 220B parameters. 84.4% on MMLU-Pro. Ranked 43rd in the world. It runs on Australian servers. Nothing ever leaves Australia, and nothing you type is used to train AI. Delete a chat and it’s gone for good. Most of the world’s AI answers to somebody else. This one answers only to you. Free to start: agentaus.com.au
1
1
3
49
so the two griftfluencer who held the $100k contest got gamed by a single griftluencer who entered the contest? proves your following count doesn't reflect brain cell count...
$100K SaaS hackathon and the winner is someone who already had an audience Funny how distribution beats building. Do you think that's fair?
1
26
Aeroslider looks lush! 🤩 i only wish it was released *before* i custom-built my own bespoke page-slider-system (but using pages has some big benefits anyway: sayso.co/) either way bookmark Aeroslider today... 🤩
Introducing Aero, the slider library for 2027 CSS-first, native scrolling, zero layout shift, 7.7 - 10.6 KB with no dependencies and was built to handle e-comm use cases Use the aeroslider.md to guide AI agents aeroslider.com
29
its a solid swap — i moved to @OpenBot_ after the great Grok Robbery-Rugpull and also enjoy Openbot more than Grok too @opencode is my primary sub and their Go plans give unbelievable usage for just $10 and $40 (including access to Gemini, Kimi, Grok, GLM, Muse, and more)
My current AI stack 1. @OpenBot_ I replaced GrokBot with OpenBot 2 weeks ago - best decision I've made in months. After the whole usage issue a few weeks ago, I knew I couldn't rely on Grok anymore. I didn't want to end up in a situation where I have shit to do, and Grok rugpulls me with the usage or replaces it with an idiotic model to save on costs. I tried out a few and Openbot's my fav. It runs on my Claude subscription, so I'm always on a frontier model instead of whatever GrokBot picks under the hood. And my usage issues are gone. OpenBot runs locally on my Mac mini. Even though people view OpenBot as a GrokBot replacement - it's starting to add new features which makes it even better imo. threaded conversation, agent docks, library, etc. 2. Claude: $200/mo Ultra plan My main model. I use Opus 5.5 day to day and switch to Fable 5.2 for the hardest problems. No explanation needed, Claude's simply the best. 3. ChatGPT: $20/mo I mainly use it for image generation and whenever I want a second opinion. 4. GrokBot: $30/mo The one thing I can't replace is Grok's native X integration for research. So I run GrokBot as a bot inside OpenBot: • My OpenBot agent sends my message to GrokBot over a webhook. • Grok does the work and drops its answer into a shared folder on my Mac mini. • My agent reads it back to me. So, it feels like chatting with any other bot. 5. OpenRouter: pay as you go One account and one API key give me pay-as-you-go access to the models I don't subscribe to, like Gemini, Qwen, Kimi and Grok. They mostly power my Mixture of Agents skill, and my agent switches each one to its newest version every week. Say you're making a huge decision. Ask Claude and you get one answer. But what if you could get several perspectives from different AI models and end up with the best version? a. Fast mode: Claude writes one version and ChatGPT writes another, without seeing each other's. Gemini grades both and picks the winner. Then my agent writes the final version from the winner, adding the best points from the runner-up. b. Full mode: Claude, ChatGPT, Gemini, Qwen, Kimi and Grok each write their own answer, and so does my agent. They grade each other's work blind, never their own. A model that didn't write the top answer turns it into the final version. Then Grok, whose job is to disagree, tears it apart before I see it. Fast takes a few minutes and costs cents. Full takes about half an hour and a few dollars, so I save it for the big calls. Everything's moving so fast so it'll probably end up looking different next year. Anyways I spent a lot of time testing diff things out and reached a setup I'm very happy with.
1
47
which one transports to the Airport?
Public transport in Melbourne
1
169
if ai fails to end humanity, humans certainly will...
This is the first gameplay clip I saw, and I was surprised to actually feel kind of grossed out by it. Don’t get me wrong, I will definitely still play this game, but as the graphics get more realistic these scenes become more off-putting
24
the grifters who just keep grifting... 🫣😶‍🌫️🤭
So in a contest to make the most $ possible, 72h after, the 2nd is at $50 0.5% managed to make at least $1… Yes, 0.5% Yet 80% of those people will buy a datafast subscription, watch Marc’s videos, quit their job to get the same lifestyle Fucking sad
21
❤️🇯🇵
Happy Japanese Language Education Week! We partnered with actor Kōji Yakusho to encourage you to study Japanese! Kōji Yakusho is an acclaimed actor known internationally for his roles in Shall We Dance? (1996), Perfect Days, Did Someone Happen to Mention Me?, and Vivant!
35
self-promoting but pretending you're not is pure deceit reflecting you and your product its what inferior products do if your product is good enough other people will promote it
crazy that you can use this app with free models from opencode grok bot like experience but for free
2
1
61
grok seems too grubby to use anymore rugpulls break trust and create distrust im happy to grok free and in an alt version that's agent agnostic
If you are using Grok Bot, don't have it do coding work directly. That is going to burn your tokens, and leave you upset about usage limits. Instead, pair your Grok Bot Ultra sub with an ultra level coding sub from one of the frontier labs. Both Codex and Claude Code have CLIs available. Grok Bot can install these CLIs on its virtual computer, and can orchestrate their use to do your actual coding work. Have them execute that coding work in their cloud environments, and not on the virtual machine itself (it can overload the VM ...). This allows you to spread the token burn across two subscriptions, and allows for more specialization at the agent level. Grok Bot is your orchestration layer, Claude / Codex are your implementation workers. The results are killer!
16
the same supreme service just looking all lovely & new ❤️ @Netlify
Today we’re launching a new Netlify. New brand, new website, new app experience, rebuilt from first principles. It’s the biggest change in our decade-long history, and it comes from a bet we made on ourselves. This is just the beginning. netlify.com/blog/the-next-de…
1
2
76
deserved too — if you're not subscribed to @denicmarko's Sunday secrets, you should be...
Google seems to like it too. markodenic.com
1
1
77
likewise – its hard not to love @Netlify they'll always be my first online love (platform) and they've been the most reliable online love too 🥰❤️🥰
Regardless of where I work, and what I do, I'm always going to cheer on @Netlify. So excited for @biilmann and the team on the rebrand and releaunch. Incredible team. Good cook y'all.
4
136
Regardless of where I work, and what I do, I'm always going to cheer on @Netlify. So excited for @biilmann and the team on the rebrand and releaunch. Incredible team. Good cook y'all.
New mission. New brand. New website. New Netlify. ✨ Turn your imagination into reality. Describe an app, build it with agents in a live preview, and developers and your agents can pick it up in Git or your own preferred tools. Check out @biilmann’s new video.
6
2
1
21
1,189
Howdy all, I am looking to connect with fellow AI & Tech Enthusiasts! Especially: - Business Analysts - Startup Founders / Entrepreneurs - Indie Hackers - Experimenters / Makers If you are building or learning something interesting, share it here. I would love to connect!
26
1
17
727
sayso retweeted
Replying to @norbertbodziony
fix the model selector UI pls 🙏🏽 it's currently woeful UX/UI even just moving it would improve everything that must be easy to do!
1
1
10
1,238
when i grow up i wanna pay @VertRect to do all my work... 🤩 😍 🤩
made with mk-mmd and Opus
30
.@OpenBot_ is a beautiful experience overall but some of the UX/UI is bad beyond-belief... 🫣😶‍🌫️ the worst culprit is the model selector for these 2 reasons... 🧵
3
3
164
1) the model selector is a million miles away from the input box so your eyes can't quickly/easily see what model you're using and you mistakenly use Fable 5.2 when you wanted to use Muse Ember (burning your @claudeai tokens on a trivial insignificant task) 😭
2
1
25
i appreciate @OpenBot_ alot, and love all the new features. but i wish they fix the monumental fundamental issues...
4
Replying to @akaSAYSO @claudeai
2) the model selector input is truncated for no known reason in the world so you can never see what model you're using (even though there's so much empty space available in this they row could display it in full 10 times over) 😶‍🌫️🫣😭
14