jFriedensreich

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”.

One of my favorite documentaries, also because it captures so much personal reality and feeling of what it must have been like, it really inspires me.

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.

A permission broker for deno + opencode fork that can run in deno instead of bun.

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.

And new prices for playing cards not even set yet... TIL nintendo still makes cards in japan.

Same reason linux or databases need to be open source. A sandbox is not a nice to have or a feature anymore, it is as fundamental building block to running any software. You cannot depend on closed source building blocks, not as closed source product and especially not as open source product.

What do you mean "not free as in beer"? Its not free as in anything? Sandboxes need to be open source, nothing else is acceptable.

Not really, its more like saying no one needs another windows when linux exists. By "no one needs" i mean the world needs open source sandbox building blocks that are up to the challenges of the current age, no closed source solution can be a fundamental building block for the world to become better and more secure. No non-local building block can be at the foundation to anything that makes the world better and more robust.

I had to dig hard to find this is a SAAS sandbox offering not an actual sandbox (the software i can use locally). Its just wasting peoples time, no one needs a non opensource sandbox. There are now at least 3 apache 2 projects (smolmachines, microsandbox, boxlite) working on sandboxes and at least one of them should be ready for primetime soon.

We still have not the right sandbox and PR abstractions to make the merge of the two complete. Imagine merging a PR and knowing exactly this code cannot ever possibly reach the internet and it can only receive and send specific shapes of api requests from these specific services, it has well defined resource limits and you have specific optimal UI to review these constraints. I can imagine to not review a bigger number of PRs in that reality.

I nearly fell for it until the tiktok part, thanks for amusing shitpost

Most software has a few years lifetime and nearly no users. What you say is only true after reaching a certain milestone like product market fit. I think the idea is to reach that turning point as fast as possible and then rebuild the system from ground up with maintainability and quality focus.

Bun is basically a lost case in the same way that claude code is. Many people love both and thats fine as long it is their personal choice. But freedom loving orgs can never ever depend on either for anything ever or build anything on top. The main problem in this picture is projects who don’t understand or remember the internet explorer hell are using bun only features to a degree that you cannot just switch. Even opencode who should have the biggest aversion to depend on anthropic is doing this and it drives me insane. Have you all lost your mind or let your agents blindly lock you into whatever hell wants to own you?

Its completely impossible to trust an article when half the diagrams have serious issues and headlines are worst slop indicators. I am sure the author is knowledgeable and spend some time on this. But please please, with butter, please, either spend the last 10% to get rid of these issues or just don't publish it! Keep it in your ai research gallery or if you want to publish that gallery as ai research?

An aspect i don't hear about enough is using agents to make better abstractions instead of treating the agent as the abstraction. We could work on making abstractions that allow expressing what we are building in most concise form without any boilerplate. The reviews are enjoyable, if llm providers fail we have a chance to use the great abstractions by hand. The alternative i see everywhere: We don’t care about the bad abstractions because agents write the code. We don't review because its too much and too noisy and we rather blow our brains out than manually dig through that react and spaghetti codebase and writing all the boilerplate and cross references by hand. We have to build for resilience and future us.

The thing is, devs with AI psychosis often work on memory systems and harnesses as part of their delusion, so i would not rule out you have it!

Where is the part where the author overcomes ai psychosis? Reads like digging in deeper and deeper.

The title is highly misleading, they mean the harness belongs outside the sandbox the agent is working in. Please run also the harness in a sandbox, i don't think any of them is safe for a host. This is also the only valuable info in this marketing noise article. The rest is full of hidden endorsements of VC buddies (why would anyone build on closed source sandbox abstractions and claim alternatives need 1s to boot) And signs they cannot reason logically. (eg. Need shared files across users > the only two options are building distr. filesystem or storing in a database. Later admitting even the database solution needs a last write wins resolution on top and completely ignoring they could just as well have delegated shared writes to a authoritative file server with retry on conflicts and git.)

Why would someone want a beige or brown fan? If it is that complicated why not only make black ones?

Looks less interactive than the actual browser debug tools... How does this help anyone? Looks like slop, why is it on front page?

I don't think this should be dismissed as a cheap and rude ripoff. I'm no expert in trademarks or the naming convention part of the story, but for the rest: warp is not a great company taking far too long to roll back its weird account requirement, tracking users, enshittifying the core terminal experience with often unwanted AI and other crap features and dismissing annoyances that are brought up by 100eds of users. We need to show companies they need to behave or will be crushed by the community.