The security boundary is difficult everywhere, here we have at least a clear baseline with decades of experience where we can slowly build from. For critical parts that don't fit on the web platform you can always fall back to a helper daemon with mutual tls or something like that. There is nothing preventing WebApps to be installed once from a good source, in fact i think this format would be a great foundation for such an electron successor. The direction of signed IWA web-bundles where the origin is a cryptographic identity seems to be a good starting point, but there is obviously still a lot to do. At the minimum we need a web of trust distribution model combined with automated scanning and completely rebuild permission and capability UX.
I was a fan of deno because at least they tried, its not that there was an alternative runtime that tries to do permissions right or that there is an operating system tool that allows async(!) permissions with user interaction. We really need a simple to use "productised" but true open source solution that allows halting any software and evaluating policies for run, fs and network etc and can reason on process and context level.
This is whataboutism. There is still firefox as possible second engine impl and you are arguing its better to not have a layer at all than accepting the possibility google might take it away. Plus most people are on macs or windows where there are at least as bad actors playing against them.
The question is at what cost and at that level of both being optimal does it even matter to the user or is indistinguishable. There will always be 1% native apps that make sense, i'm talking about 99% of applications.
I am at the opposite extreme. We should ditch electron and use browsers good enough integrated they can run all the apps with native feel and reusing the same engine (not a lacklustre OS webview but a complete one) This solves the memory overhead, solves unpatched or misconfigured chromium in each electron app as well as portability and reusing web dev skills. Also this would allow permissions and security to be managed by a layer that can focus on that and I don't have to worry about what a native app can do. (OS permissions and sandboxing are just not made for vibecoded infinite software and likely never will catch up) All the performance and other arguments are just not true, a well build webapp is often more performant than a native app especially for long scroll lists not even to mention accessibilty, extensions and more. I will never trust discord or Spotify to run something natively on my machine and so should no one else.
I see nothing this brings over smolvm machines. I did not use lima / krunkit outside colima but in colima it was just slow, had outdated devx and was unreliable compared to controlling every detail with an embedded vm library.
The author misapplies/misunderstands the mythical man month even in the first example. It does not apply for idea generation and also not to problem solving/ fixing things, only to software creation. Even then, it also does not apply when creation is cheap, if you can generate 100 solutions cheaply without coordination between them and pick the winner with a relatively fast eval, creation behaves way more like fixing / problem solving.
what proxy is he using? i support not trying to support a specific product in a post but not even mentioning what you use after writing this seems pretty odd.
Any details about the streaming ui lib they mention or about the format of the ui code? This could become really annoying to be fractioned among model providers with custom RL that required independent tools like open code to use each providers custom streaming UI libraries.
the answer to facebook being bad is obviously not block-listing but allow-listing content. we had the same learning in security years ago. what this might look like is ai assisted desired data extraction and using clients tailored to user needs and user agency to use that data. Unfortunately alternative platforms that are user aligned are not the solution as you cannot force your whole cities groups or old family members to move which is the main pain point for people who use adblockers and still also on facebook.
yes, especially compared to deno bun does not have proper isolation or permissions at runtime layer which is why anthropic tries to fix the lack by a mixture of app layer (build into claude code) and os layer (srt) however using runtime permissions would allow much better security if done right.
What the hell, as far as i see this is not open source but has the tag line "Meet LM Studio Bionic, the AI agent made for open models" How can someone justify this complete clash of values, who is even an audience for something this. cursed, the agent and harness layer being open is probably more important than your models as you can just switch models every week and they are commodity.
I am confused by this article landing on front page, it does not seem to contain any new insights but besides mostly reading ok falls apart when mixing up model and harness comparison in an amateurish way. Why would the subpar search tool zai provides be relevant for comparing models? They did not even mention the >capability< to use said tools but talk about MCP/ search providers as if thats not an implementation detail.
separation of model and tooling is as important as legislative and judicative, and just ignore any tooling or harness not true open source. they will all slowly creep into your life and choke you trying to lock you in.
Does this even still matter? No good behaviour in the world can restore trust in claude code and in fact all of Anthropics tooling, apps and harness teams except the core model research which still produces great models but seemingly losing ground to z and openAI. The GLM 5.2 hype and the limited impact of the fable lock down should be clear signals that models have no moat and frontier labs will do anything in their power to lock users into their toxic ecosystem of tools and taking context hostage.
This issue was what had me give up on windows forever and its been around since forever. There are many situations when there is just no way to release files except restart. When the basics don't work nothing else even matters.
ps the refactoring it did as part of the solution was a bit verbose and had a few abstractions i knew would not be needed and asked it to remove but were solid otherwise.
I had a pretty involved cross module state bug with complex dependencies and also reactivity issues interleaved. I tried fixing it multiple times manually with 4h time box as well as claude models up to opus 4.6 high and codex 5.3 all which failed. When the GPT-Pro model came out i heard it was not supposed to be an everyday coding model but tried anyways as it looked impressive. It took a single 8h run burning 200$ with doing nothing but occasionally waiting for test runs or me writing “continue”. After 8 hours, and fearing i wasted the money, the bug was consistently fixed, not just one edge case that triggered the behavior.
As a society its good for resilience to embrace small pockets of complete ai withdrawl. We should be happy some groups go through pain to keep best practices and processes alive that do not rely on any ai whatsoever. But most of these are unbearable for pragmatic normies to be around. This is made worse by the fact that seemingly a high percentage is not fully motivated by morals but by a deep insecurity that makes them militant, overly judgmental, bipolar thinkers and prone to weird authoritarian dynamics and exclusionism that i only know from the “vegan power” hatred for vegetarians and militant antifa s hatred for the “realist left”.
The only thing missing i could find was https://en.wikipedia.org/wiki/Dashcode which had a pretty great data binding UI that i never quite saw like that.
Never found a good application for any of these immutable js data libraries. Maybe it could be helpful to prevent bugs in middleware chains of expresslike backends but for ui libraries it always felt like the libraries basically recreate mutable data structures with virtual proxy objects but at that point what does immutable even mean? you have completely virtual objects and can do whatever you want to make the rendering performant and reliable, at that point it would look probably more like a data binding layer with virtual objects to something like tanstack query
I still don't understand how people consider bun as a viable runtime when its owned by evil corp trying to use it for capture of the tooling layer and its the most insecure runtime on top of that. Meanwhile deno is performant and has dramatically improved node compatibility while exposing a proper permission broker api.