Providing feedback spatially is precise without words. Its a massive workflow win because is quicker and you don't lose focus by switching your focus.
The laptop stares at itself in the mirror while an AI recalibrates the optical parameters, piloted from a nearby phone.
Dug up my fast optical localization project and finally got it running pose tracking direct from webcam feed. The AI managed to optimize its performance down to "3 ms/frame" in the browser! Not bad but I am aiming for *much* faster on real hardware. tomlarkworthy.github.io/lopebooks/no...
OK one of the greatest things IA've ever built. Bi-directional SVG source code editing. Drawing as programming with programmable drawings. *this* is how I want computers to collaborate with me. Ordinary SVG with a plurality of editable views. tomlarkworthy.github.io/lopebooks/no...
Claude Code's TodoWrite tool has gone? How do I sequence a long list of tasks now?
randomized property testing is a cheap version of theorem proving reachable in a mainstream programming language. So I am seeing better code produced by getting the LLM to create a theory of a domain, and then property checking its parts. Then the architecture becomes assembly by an algebra.
As agents hammer all free services on the internet, and automate what was previously un-automatable, you will need to hunker down and work offline to get any serious work done i.e. @localfirstconf.com
wow this website is jammed full of interesting details.
Just published a blog post about the new CSS Anchor Positioning API! ⚓ I’ve been learning about it over the past few weeks, and it’s friggin’ great, but it also took me a minute to really get the hang of it. My goal in this post is to share the most useful bits, so you can start using it today. 🔥
I am not blown away by Fable. It can do some advanced coding but it still can't accomidate out-of-the-box thinking and spatial intelligence is still non-existent.
I been trying to understand why my notebook coding agents suck compared to Claude Code. What is different? Its not the prompt or the task or the LLM... it was the environment and tool design. did-plc-j7nm3lrd5h7fm3sfhcv3lhfv.lopecode.com/r/coding-tools
So many new features in a single image! Try and spot them all 👀
Building on OpenRouter is the correct choice if: 1. You think AI can be useful 2. You are concerned about big LLM providers becoming too powerful. 3. You don't think it's realistic that everyone will have the hardware to run locally
Build your own always up-to-date Feeling of Computing newletter Based on the amazing work by @larkworthy.bsky.social live sync-ing slack to at-proto Try it here: marianoguerra.github.io/Feeling-of-C...
I been working in the shell since February and I am sick of it. I gotta get agentic coding working in a notebook with visual feedback just because it is so much more stimulating than the shell. I hate the shell.
Scratch is better than I remember it. define blocks can execute immediately and outside the animation loop so you call them recursively and do multi sprite spawning in a single tick which is quite handy for generative stuff.
A strange but effective regularisation strategy for LLM prompt optimization is telling it not to overfit e.g. Don't use examples based on the test set. Then it doesn't.
Just thrown out the VGA cable I have carried around for years. Probably not gonna need it...
Yeah I think basically bash is the strongest meta-interface to anything for a LLM. "everything is a file" includes virtual abstractions created inside that virtual fs. The file system *is* the interface. The LLMs are tuned so hard on TerminalBench they are shell ops masters.
Lopecode newsletter-001 Read all about the newest addition to a local-first reactive notebook environment that can be published to ATProto did-plc-j7nm3lrd5h7fm3sfhcv3lhfv.lopecode.com/r/newsletter...
✨ Atmosphere devs ✨ Bluesky is integrating Standard Site, and our initial work should be released in the next few days. Here's what that means for publishers and apps in the ecosystem: github.com/bluesky-soci... If you have questions or comments, please leave them on the GitHub Discussion thread!
Integrating Standard Site Into Bluesky · bluesky-social atproto · Discussion #4978
The Bluesky team is working on integrating site.standard.* lexicons. For people using the Bluesky app, this means that when they come across a link published with a Standard.site record, they’ll ge...
github.com
the end of "parametric abstractions". A config menu, a set of arguments for a function, they are parametric. They have a certain specified configuration space. Its what we have always done. Its core to functional abstraction. With on-demand code generation, the space of programs is non-parametric...
Oh interesting. I added the computeNow ticks of the Observable runtime to the new debugger, and now I can see that cells that have a long compute time end up eating ticks from the runtime. Did not know that!
How hard would it be to replicate a community Slack installation to an ATProto lexicon so messages can be archived or sent to other application for indexing? Is there any community lexicons for this already?! cc @bmann.ca
Working on the next version of the temporal debugger for Lopecode. Now the "blocked" vs "computing" difference is colored, and the cells are topologically ordered so you see the cascades of computation much easier. Its already revealing a ton of unexpected inefficiencies!
Worked on getting themes reactive which was oddly satisfying. My favourite is ocean-floor
My experiments with hosting notebooks on atproto. The Ledger notebook lets you manage your notebooks and cross-post them, like I did just now!
It used to annoy me that Safari and Firefox would surface bugs that chrome did not have but now in my wiser years I am thankful there is divergence and multiple vendors for such an important technology as the web. The bugs are fixable, ecosystem capture cannot.
We are having some fun in the malleable systems forum collaboratory forum.malleable.systems/t/collaborat...
Collaboratory for Advanced Malleable Systems Research
“Collaboratory” is a portmanteau of collaboration and laboratory, a word that came to mind while thinking about how empirical research and the experimental method can be applied to further our underst...
forum.malleable.systems