Slayga
177 posts


@GeoffreyHuntley What about frontend tho.. opus (4.6) still ui king
English

Great time to cancel your claude max and try a real harness that actually cares about how you work with access to all the best models
Factory@FactoryAI
Introducing our new $100 Plus plan. We've been listening to your feedback and are excited to offer more flexibility and horsepower with this plan. Plus offers ~5x the usage of Pro and gives you access to Droid Computers so you can run remote Droids. We can't wait to see what you build.
English

speaking tour coming to an end soon. two more in two weeks. then rest, then resuming @latentpatterns build 🥹
✅ blackbird
🔜 heavybit sf
🔜 ai engineer singapore
Blackbird@blackbirdvc
🌅🌅🌅🌅🌅
English

@Mattslayga @Railway Would love to, but we're scaling absurdly quickly as is
Most of our focus on doing "less but better". We will assuredly add more regions in the future, once we finish this new experience we're working on
English

Folks, if you are mad about LLM providers' subscription policies, there's a simple answer: Use a third-party harness that lets you switch providers at will, and pay usage-based API price. No subscriptions.
It might be more expensive for now, *if* you choose a frontier model for every task. But the easy switching means you can choose cheaper models (like Kimi or GLM, which are getting pretty good!) for a lot of things. And in the long run, API pricing will be driven down by competition.
This is what the LLM providers really don't want, but the rest of us should all want. If we don't want all the value created by LLMs to be captured by the LLM providers -- if we want the value spread across the economy -- then we need to make sure they are in perfect competition.
Bonus: No stressing about running out of quota (nor failing to use up quota before it resets). You get exactly the tokens you need.
English


@ClaudeDevs Was there an outage? I was getting 403s everywhere then met with this. I'm thinking it's about time to jump back on the @FactoryAI sub.

English


I'm using gpt 5.5 xhigh while designing a table schema and it feels dumber than 5.4. but not a strong feeling
it's formatting of output is different as well. It's not wrong, but different, feels more terse than 5.4
maybe it's better at instruction following, and it's picking up on my previous use of plain-language skill

English

Holy shit was not expecting to laugh that hard. Well played 👏
Rohan Varma@TheRohanVarma
For clarity, we are running a small test for ~100% of Codex users where we: - make our best models available to all users - make Codex available to all plans, free and paid Claude Code users aren't affected :)
English

A friend asked me the other day “how have you been” and I literally had no idea how to respond
Craig Weiss@craigzLiszt
being a founder is weird. you become inherently unrelatible to 99.99% of the population
English

ChatGPT Only Reads 15% of Your Files (Proof) youtu.be/k3vjB8VrmNU?si… via @YouTube
Was just shared this, I think this validates what a lot of people have been feeling recently. Why I personally don't use chatgpt as a product at all anymore.

YouTube
English

@metapreston Clawdbot? Super easy to use after 80 hours of reading guides and investing in a VPN or Mac mini
English
Slayga retweetledi

PSA: You do NOT need to buy a Mac Mini to run Clawdbot 🦞
That dusty laptop in your closet? Works.
Your gaming PC you feel guilty about? Works.
A $5/mo VPS? Works.
A Raspberry Pi held together with hope? Probably works.
The M4 Mac Mini is gorgeous but Clawdbot runs on basically anything with Node.
Stop giving Apple your money (unless you want to, I'm not your mom).
👉 #do-i-have-to-buy-a-mac-mini-to-install-this" target="_blank" rel="nofollow noopener">docs.clawd.bot/help/faq#do-i-…
English









