I'd wager that a "main agent" is really just a bunch of subagents in a sequential trench coat.
At the end, in both cases, it's a back and forth with an LLM, and every request has its own lifecycle. So it's unfortunately at least a networked systems problem. I think your point works with infinite context window and one-shot ting the whole repo every time... Maybe quantum LLM models will enable that
Yeah for sure but I think frameworks will adapt. It's like going back to 2002 and saying that it's better to program in Java because of all the IDEs available and all the corporate money being poured into having the best developer experience there can be. But since LSP arrived, developers choosing a smaller language suffer much less.
The 'LSP' that would allow new frameworks or languages to shine with coding agents is already mostly here, and it's things like hooks, MCPs, ACP, etc. They keep the code generation aligned with the final intent, and syntactically correct from the get go, with the help of very advanced compilers/linters that explain to the LLM the context it's missing.
That's without hypothesising on future model upgrades where fine-tuning becomes simple and cheap, local, framework-specific models become the norm. Then, React's advantage (its presence in the training data) becomes a toll (conflicting versions, fragmented ecosystem).
I also have a huge bias against the javascript/typescript ecosystem, it gives me headaches. So I could be wrong.
I don't buy it either. I've been building my own backend framework for the past 2.5 years, and even though it's a DSL over Python and there's no documentation online and barely one in my computer, Claude Code understands it with enough usage examples in my codebase.
In front-end as well—I've been able to go much farther for simple projects using alpine than more complex frameworks. For big products I use Elm, which isn't exactly the most common front-end choice but it provides a declarative programming style that forces the LLM to write more correct code faster.
In general, I think introspectible frameworks have a better case, and whether they're present in training data or not becomes more irrelevant as the introspectibility increases. Wiring the Elm compiler to a post-write hook means I basically have not written front-end code in 4 or 5 months. Using web standards and micro frameworks with no build step means the LLM can inspect the behaviour using the chrome dev tools MCP and check its work much more effectively than having to deal with the React loop. The ecosystem is so fragmented there, I'm not sure about the "quality because of quantity of training data" argument.
I am curious actually! In general about your experiments, but also about integrating this detection algorithm to wider systems. Did you run any autogpt-like experiments with the AI generated text as a critique? My use case is a bit different (decision-making), so I play with relative plausibility instead of writing style. But I haven't found convincing ways of "converging" quite yet, i.e. benchmarks that don't rely solely on LLMs themselves to give their output.
He mentions it in the video. They couldn't rely on Elm, which was too young at the time, for their migration away from Flash. The scale of creating a language was too big for Prezi's immediate needs back then
No, life goes on and it's not a calamity. It's pretty bad, but we'll have another crisis if tourism goes down because of the bad publicity of the earthquake.
For many Moroccans, welcoming tourists is their livelihoods. The best thing you can do to support them is to keep your plans in place.
I'm curious what companies stand to gain the most from this discovery... I understand the promises of LK-99, but where do you think where we'll see it be applied first?
As an Arabic speaker, the verse in the Qur'an means to me that fasting helps you remember Allah.
Islam has no concept of empathy for all beings, or enlightenment really. The assumption is that without the fear of God and Hell, people would sin by default, and religious practices are meant to please God.
Often progressive Muslims mention Sufis but they have been persecuted enough, for holding God-consciousness type beliefs amongst others, to consider them a different thing altogether.
In my use case, I find the lack of features of msgspec more freeing in the long run. Pydantic is good for prototyping, but with msgspec I can build nimble domain specific interfaces with fast serial/deserialisation without having to fight the library. YMMV!
Title slightly misleading... The article makes the point that downtowns are turning from office to social centres and the $453B figure is more of an investment in repurposing offices and rethinking urban spaces for that purpose.
I welcome these changes... Yes we'll need to rethink our urbanism, but if anything this switch feels like a coming back of what our urban centers are supposed to provide us.
Imagine parking spaces becoming local artisans/food stalls, conference rooms becoming event spaces, coworking spaces adapted to people's lifestyle and living patterns (e.g. a suburban cowork with childcare and a dog park).
"gutting downtown" might be true for those who are wary their office real estate investment will not have a positive ROI. But the way I see it, this change in urban patterns is a paradigm shift in wealth distribution patterns and in economic opportunities for leisure services, both locally and globally.
I think the difficulty in finding other examples is reflective of the "emergent"/"meta modern"/"systems thinking" space being extremely heady to this day. The people there are good at conceptualizing how to maintain a well running group horizontally, but growing one anew requires a different set of skills and traits. Chiefly knowing what's important right now, whereas the emergent thinkers seem to get lost in the weeds of their thoughts and big words.
That field is also, in my humble experience, in a bind. Very few people outside of the coach/consulting sphere seem to talk about this as fervently as they do. I think mass adoption will require the concepts to be attractive and simple to people who may not be ardent supporters of the cause quite yet.
There's also a whole contingent of people who have built orgs that already do this, they just don't advertise themselves and do their work.
I think the next step is to deeply integrate the concepts of Enspiral and such into organisational design tools. Something like murmur.com but with a super low conceptual barrier to entry, that makes it obvious what the next distributed leadership shift is for a given group. That's what I'm developing, if you're curious contact me :)
Not in the tech field but in the consulting space, both Crisp https://dna.crisp.se and Enspiral https://enspiral.com came up with interesting organisational structures that they've extensively documented.
Wayland's biggest disadvantage is that I can't use my computer as a heater anymore. With X11, I had that feature everytime I would try connecting a second screen to my HiDPI laptop.
Honestly though I don't get the Wayland hate. It's been stable to use and a joy to configure. X11 survives because of legacy and inertia, and I haven't looked back one second since the ~3 years I made the switch to Wayland/Sway.
At the end, in both cases, it's a back and forth with an LLM, and every request has its own lifecycle. So it's unfortunately at least a networked systems problem. I think your point works with infinite context window and one-shot ting the whole repo every time... Maybe quantum LLM models will enable that