The slop drowning and impinging our ability to do good hammock driven development.

Love it. Thanks Bryan.

It's invaluable framing and we'll stayed. There's a pretty steady background dumb-beat of "do we still need frameworks/libraries" that shows up now. And how to talk to that is always hard. https://news.ycombinator.com/item?id=47711760

To me, the separation of concerns & strong conceptual basis to work from seem like such valuable clarity. But these are also anchor points that can limit us too, and I hope we see faster stronger panning for good reusable architectures & platforms to hang out apps and systems upon. I hope we try a little harder than we have been, that there's more experimentation. Cause it sure felt like the bandwagon effect was keeping us in a couple local areas. I do think islands of stability to work from make all the sense, are almost always better than the drift/accumulation of letting the big ball of mud architecture accrue.

Interesting times ahead. Amid so much illegibile miring slop, hopefully too some complementary new finding out too.

Amazingly frank talk from Peter: https://telex.hu/belfold/2024/02/10/magyar-peter-varga-judit...

I really appreciate this comedic take from Bluesky:

> analogy for the America brained is like if the Dems lost to Trump four times in a row and then ran Mitt Romney to save the country and won crazy supermajorities and also Mitt Romney was named Johnny America https://bsky.app/profile/michaelcaley.bsky.social/post/3mjd2...

I find it emptier than the calories you condemn. And of worse character than the people you so impugn upon.

Why? Why not make a more enjoyable world? Why insist in denial? It's so confusing to me that such bitterness and aggressive zeal, such negative energies, go so unchecked. And for what?

I hate to drag an innocent into my countrr-tirade, but Paul Ford writing about mounjaro/glp-1 was a great article for raising this issue that medicine has fixated upon a correction of disease, leaving it adrift at dealing with the questions of what happens if biotechnology can make us better. Not just correct the wrong, but give us that better living through chemistry (etc). It's so tiring that the progressive possibilities we encounter out there always spark such fierce negative clawing us backward condemnations. It's all a hill of supposition, a politics of fear & scaring. https://www.wired.com/story/new-drug-switched-off-appetite-m...

I do think there are amazing human characteristics of restraint & measure, that have to be developed. But I don't necessarily know that projecting that onto our food or how we manage our weight is particularly an important load bearing piece of that human character. I don't think anyone knows that. And it seems like we're back at this constantly repeating juncture: we can improve how enjoyable life is for many, and, "this has made a lot of people very angry and been widely regarded as a bad move." -DA

I cannot state enough how strongly I think people should have some accountability at least to their flagging. This ability to remain an Anonymous Coward while suppressing such vital stories at the heart of this world and it's tensions is exceedingly fallen.

At a minimum there ought be a system to out the flaggers. My gut says flagging should be a public action, period.

The reply seems to be: oh huh, interesting. Maybe that's a good thing since people sometimes one-shot? That doesn't feel like the messaging I want to be reading, and the way it conflicts with the message here that cache is 1 hour is confusing.

https://news.ycombinator.com/item?id=47741755

Is there any status information or not on whether cache is used? It sure looks like the person analyzing the 5m issue had to work extremely hard to get any kind of data. It feels like the iteration loop of people getting better at this stuff would go much much better if this weren't such a black box, if we had the data to see & understand: is the cache helping?

It's not at all about picking popular tech: that's what the limitation used to be. Now it's all about finding the best winds to have at your back.

Reducing your app code complexity, having a better defined more cohesive base to build upon will reduce reasoning costs & token count. It will also make it easier to assess what you+agent have built too.

I love tanstack's rich front end. Ya'll have quite an amazing system, and I'm wondering if there's any thoughts on how perhaps your pretty substantial front end side might be adapted to tanstack DB. https://github.com/TanStack/db/tree/main/packages

> I keep seeing Lit gain adoption in gen-UI.

> Lit's plain JS/TS, no-build-required approach is easy for LLMs to generate and for harnesses to integrate.

> If a gen-UI pre-viewer can load standard JS modules, it can load Lit components. No custom Angular, Vue, or Svelte toolchain integration needed.

- Lit author, Justin Fagnani, https://bsky.app/profile/justinfagnani.com/post/3mj376ogels2...

It so unsurprising that these dark days would have an administration that argued it owes nothing to the American people, nothing to history. That they would want to hide their filthy destruction.

Back in 2018, Trump used to go around violating the law with his bare hands, ripping up documents that displeased him. Pitiful staffers were assigned to go tape the documents back together, in some sign of respect to the law & history. https://boingboing.net/2018/06/11/presidential-records-act.h...

I strongly dislike the "everyone is 12" or everyone is 15 tale being told now, that there are no adults. There are adults. They are all just wicked evil people working against America, are the pardoned insurrectionists and much much worse, with far more focused reign to do what Reagan and the Powell memorandum and Project 2025 (which is but a recent update to a long running document begat from the Powell Memorandum) set out to do: to unmake America, to bypass all checks, to dynamite the nation from the inside out. Heck yes they want to make sure no one sees them TNT'ing the Union.

> The amount of energy needed to refute bullshit is an order of magnitude bigger than that needed to produce it.

Now the energy needed to secure against exploits is orders of magnitude bigger than the effort needed to secure it.

The combination of deep expertise + infinite patience of the LLM meeting the vastly increasing surface of software has a certain apocalyptic chaos gods ruin to it all, just as well known bias for mistruth to unfairly propogate itself bedevils this good planet.

Wildly & not, the contendor is a former insider. I really want to look forward with hope to something, anything other than this "strongman" (a word few such men deserve). Until this recent Guardian article, I really had no idea who, what person and what force, was actually contesting Orban & the elite establishment he represents. Having read it? Still sounds like a dark horse. And as the article says: maybe a requirement when the incumbent controls the media & uses lawfare and mediafare to harass any opposition that grows. https://www.theguardian.com/world/2026/apr/10/peter-magyar-l...

I truly genuinely wish the arsenal of democracy included less JDAMs (bombs) and many more means to rise the voice of the people & truth, megaphones for life liberty & democracy aspects. Democracy is beset by the very worst everywhere, and it is a huge struggle of all people to figure out how we connect the campaigns and governments of the world to the actual truths and day to day lives of what people live and what is really happening. When contested by such vile manipulators & deep pocketed interests & media-powers everywhere. The ability to create such thick dense mal-information hyperrealities seems like the greatest threat to the world, fundamentally obstructs any right steerage.

I hope so much Hungary really gets a chance to escape their dark isolated propogandized sick entrapped crafted fiction, and gets to come back to a truthful world. Even if this guy wins, it's a long long long haul to cast off such an incredibly biased apparatus of such wealth crafted to spin such a falsified reality as befits them. I really hope somehow against all odds Péter Magyar can work to restore the basic truthful groundings of this poor beset democracy.

But what really changed my mind is seeing how much more casual scripting the LLMs do these days. They'll build rad unix pipes, or some python or node short scripts. With CLI tools, it all composes: every trick it learns can plug directly into every other capability.

Where-as with MCP, the LLM has to act as the pipe. Tool calls don't compose! It can read something like this tmux skill then just adapt it in all sorts of crazy ways! It can sort of do that with tool calls, but much less so. https://github.com/nickgnd/tmux-mcp

I'd love to see a capnproto capnweb or some such, with third party handoff (apologies Kenton for once again raising 3ph), where a tool call could return a result and we could forward the result to a different LLM, without even waiting for the result to come back. If the LLM could compose tool calls, it would start to have some parity with the composability of the cli+skill. But it doesn't. And as of very recently I've decided that is too strong a selling point to be ignored. I also just like how the cli remains the universe system: if these are so isomorphic as I keep telling myself, what really does the new kid on the block really bring? How much is a new incarnation better if their capabilities are so near? We should keep building cli tools, good cli tools, so that man and machine benefit.

That said I still leave the beads mcp server around. And I turn on the neovim MCP when I want to talk to neovim. Ah well. I should try harder to switch.

I wish I was keeping better track of them all but there's a bunch of neat tmux based multi-agent systems. Agent of Empires for example has a ton of code around reading session data out of the various terminal uis. https://github.com/njbrake/agent-of-empires

Ideally imo tui apps also would have accessibility APIs. The structured view of those APIs feels like it would be nice to have. And it would mean that an agent could just use accessibility and hit both gui and tui. For example voxcode recent submission does this on mac for understanding what file is open/line numbers. https://github.com/jensneuse/voxcode https://news.ycombinator.com/item?id=47688582

> When you press the hotkey, macOS Accessibility APIs read the selected text and line numbers from the active editor window. If the Accessibility API doesn't return selected text (some apps don't support it), Voxcode falls back to simulating Cmd+C.

Regarding working with code, I've quite enjoyed using the mcp-neovim-server. Asking it to show & select pertinent lines can be helpful, especially when there's multiple file references at once. Turning this around & asking the LLM to get data out would be possible, but as you say, this would be IDE specific. Ideally there would be some good cross-IDE MCP tools. https://github.com/bigcodegen/mcp-neovim-server