FINDarkside

When stuff is delayed due to "safeguards" it just means they don't think they have the compute to release it right now.

I think people are looking at skills the wrong way. It's not like it gives it some kind of superpowers it couldn't do otherwise. Ideally you'll have Claude write the skills anyway. It's just a shortcut so you don't have to keep rewriting a prompt all over again and/or have Claude keep figuring out how to do the same thing repeatedly. You can save lots of time, tokens and manual guidance by having well thought skills. Some people use these to "larp" some kind of different job roles etc and I don't think that's productive use of skills unless the prompts are truly exceptional.

OpenAi does have python execution behind general purpose api, but it has to be enabled with a flag so I don't think it was used.

I wouldn't draw such conclusions from one preprint paper. Especially since they measured only success rate, while quite often AGENTS.md exists to improve code quality, which wasn't measured. And even then, the paper concluded that human written AGENTS.md raised success rates.

Also, GCP Cloud Run domain mapping, pretty fundamental feature for cloud product, has been in "preview" for over 5 years now.

> then you should create an example repo that shows the playwright CLI and playwright MCP add the same number of tokens to context and that both are equally configurable in this respect

That's just implementation detail of how your agent harness decides to use MCP. CLI and MCP are on different abstraction layers. You can have your MCP available through CLI if you wish so.

This is very developer centric. While Github might have good CLI, there's absolutely no point in having most services develop CLIs and have their non-technical users install those. Not only is it bad UX, but it's bad from security perspective as well. This is like arguing that Github shouldn't have GraphQL/Rest api since everyone should use the CLI.

I feel like some people in this thread are talking about estimates and some are talking about deadlines. Of course we should be able to give estimates. No, they're probably not very accurate. In many industries it makes sense to do whatever necessary to meet the estimate which has become a deadline. While we could do that in software, there often isn't any ramifications of going a bit overtime and producing much more value. Obviously this doesn't apply to all software. Like gamedev, especially before digital distribution.

I think it's obvious that all software teams do some kind of estimates, because it's needed for prioritization. Giving out exact dates as estimates/deadlines is often completely unecessary.

It's certainly not uncommon to cache deps in CI. But at least at some point CircleCI was so slow at saving+restoring cache that it was actually faster to just download all the deps. Generally speaking for small/medium projects installing all deps is very fast and bandwidth is basically free, so it's natural many projects don't cache any of it.

Sure, but pnpm is very slow compared to bun.

They're not being harrassed. You're basically saying that because FFmpeg doesn't have enough resources to fix all the security vulnerabilities, we should fix it by pretending like there are none.

None of those require AI though.

It's trivial to get better score than GPT-4 with 1% of the cost by using my propertiary routing algorithm that routes all requests to Gemini 2.5 Flash. It's called GASP (Gemini Always, Save Pennies)

Right, I agree there. Also that's something LLMs can already do. If you give the problem to ChatGPT o3 model, it will actually write python code, run it and give you the solution. But I think points 1 and 2 are still very valid things to talk about, because while Tower of Hanoi can be solved by writing code that doesn't apply to every problem that would require extensive reasoning.

I think it's very widely accepted definition and there's really no competing definitions either as far as I know. While some people might think AGI means superintelligence, it's only because they've heard the term but never bothered to look up what it means.

What does "choked on it" mean for you? Gemini 2.5 pro gives this, even estimating what amouns of those 3m ships that sank after pianos became common item. Not pasting the full reasoning here since it's rather long.

Combining our estimates:

From Shipwrecks: 12,500 From Dumping: 1,000 From Catastrophes: 500 Total Estimated Pianos at the Bottom of the Sea ≈ 14,000

Also I have to point out that 4o isn't a reasoning model and neither is Sonnet 4, unless thinking mode was enabled.

Agreed. But also his point about AGI is incorrect. AI that will perform on the level of average human in every task is AGI by definition.

I don't think most of the objections are poor at all apart from 3, it's this article that seems to make lots of strawmans. Especially the first objection is often heard because people claim "this paper proves LLMs don't reason". The author moves goalposts and is arguing against about whether LLMs lead to AGI, which is already a strawman for those arguments. And in addition, he even seems to misunderstand AGI, thinking it's some sort of super intelligence ("We have every right to expect machines to do things we can’t"). AI that can do everything at least as good as average human is AGI by definition.

It's especially weird argument considering that LLMs are already ahead of humans in Tower of Hanoi. I bet average person will not be able to "one-shot" you the moves to 8 disk tower of Hanoi without writing anything down or tracking the state with the actual disks. LLMs have far bigger obstacles to reaching AGI though.

5 is also a massive strawman with the "not see how well it could use preexisting code retrieved from the web" as well, given that these models will write code to solve these kind of problems even if you come up with some new problem that wouldn't exist in its training data.

Most of these are just valid the issues in the paper. They're not supposed to be some kind of arguments that try to make everything the paper said invalid. The paper didn't really even make any bold claims, it only concluded LLMs have limitations in its reasoning. It had a catchy title and many people didn't read past that.

The benchmark also says Tauri takes 25s to launch on Linux and build of empty app takes over 4 minutes on Windows. Not sure if those numbers are really correct.

This vuln doesn't really have anything to do with that premise. Middleware always run on the server.

Yeah, "obvious" critical vulnerability that is easy to use against any Nextjs app, spend 2 weeks making a fix and then announce on Friday evening that all Nextjs apps are free game. Lovely. Luckily doens't affect any of the sites I'm responsible for, since I hated middleware and most of the Nextjs "magic" features already.

That "article" looks like AI generated slop. It suggests `if (request.headers.has('x-middleware-subrequest'))` in your middleware as a fix for the problem, while the whole vulnerability is that your middleware won't be executed when that header is present.

So let me get this straight. You've used Kafka once, RabbitMQ never. You don't really know what you did with Kafka. But you somehow know that RabbitMQ cannot do the thing which you don't really remember anymore. Doesn't make much sense to be honest.

Nobody can really have any sources for RabbitMQ being able to do it if you don't know what it supposedly cannot do. The way you descibed it, is that you simply read data and then did something with the data and passed it to somewhere else. RabbitMQ obviously can do it.