malary retweeted
Strata 1.0 is here.
The best file manager on Linux, fully open source.
45 days, 775 commits, 38 contributors, ~300K lines of Rust.
stratafiles.io
What's new 🧵
malary retweeted
Paid a small fortune for this book - I want to understand how the sudden advancement in technology+computing in 1982 should have meant the end of needing any programmers to build software
As this topic is very relevant again, with the sudden advancement w technology+computing
malary retweeted
This icon library is amazing!
Reicon gives you 2,700+ beautifully crafted open-source SVG icons for websites, apps, dashboards, and design systems.
Bookmark it for later 💜
malary retweeted
Codex tip: once GPT-6.1 Sol is your main model, stop running Astra on every turn
put Astra on call as an architect agent
GPT-6.1 Sol keeps writing the code
Astra only gets spawned at three points:
→ before a plan: is this the right approach?
→ when the same error comes back: am I digging in the wrong place?
→ before "done": what did I miss?
Astra reviews. Sol ships
Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split
- the full tree
> GPT-6.1 Sol on high runs the main session
> explorer reads the code on Luna
> worker edits and runs tests on Sol
> researcher pulls the docs on Luna
> all three on medium
> Astra on call as the architect
> auto_review checks every approval
paste the tree and this prompt into Codex ↓
"Rebuild my Codex setup around this tree:
1. Check ~/.codex/agents and .codex/agents for agents that already fit explorer, worker and researcher.
> Draft new TOML files only for missing roles
> explorer and researcher on gpt-6-luna, worker on gpt-6.1-sol, all with model_reasoning_effort medium
> Add an architect agent on gpt-6-astra, model_reasoning_effort high, whose only job is reviewing plans, repeated errors and finished work
> Skip any that pin a different model and list them
2. In ~/.codex/config.toml set model to gpt-6.1-sol, model_reasoning_effort to high and approvals_reviewer to auto_review
3. Find anything that would override this (active profiles, flags in my shell aliases, agents.default_subagent_model). Report it, change nothing
4. Add one rule to AGENTS.md: spawn the architect before a large plan, when an error repeats, and before calling a long task done
Show me every change as a diff first. No edits until I say go."
↳ developers.openai.com/codex/…
malary retweeted
bro aint wrong
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
malary retweeted
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
malary retweeted
Introducing CRIS for Omarchy.
The lightest system resource monitor on the planet.
btop: 32,188 KB
top: 6,100 KB
slstatus: 2,556 KB
CRIS: 16 KB
A program that does literally nothing: 12 KB.
CPU, RAM, Internet, Storage. 5 KB binary.
malary retweeted
Access this prompt as well as UNLIMITED prompts for stunning AI websites in one click: sceneai.art
malary retweeted
MotionSites just hit 1 million monthly visitors
Access 500+ website prompts. 100+ 3D scenes, 100+ interactive gradients, 300+ backgrounds, motion sections. Everything's a prompt.
motionsites.ai/
Thank you to the developers and founders building with us.
malary retweeted
❤️🔥 Opus 5.5 one-shoted this motion video.
Generated this in 4 minutes, only did 1 change.
Prompt
"Create a launch video for MotionSites AI, just hit 1 million monthly visitors after 8 months after launch."
That's it..
malary retweeted
Command & Conquer: Omarchy Edition is out.
You can play it now.
Build the ISO, harvest packages, and send the coding agents against Reboot Required and The Walled Orchard.
Three factions, custom artwork, one bundled Omarchy skirmish.
Your turn: github.com/tcballard/command…
malary retweeted
In 2001, we really thought this was what the future of web design would look like.
ALT 2Advanced Studios v3 website in 2001
ALT Afterlab website in 2001
ALT Designgraphik website in 2001
ALT Floodgear website in 2001
