I think some of that is because the reporting is focused on the new stuff, that was previously not possible. That human work is involved and some of the weaknesses are not really new. But also because the information in this case comes from a company that wants to sell their AI. I agree that the reporting is probably biased and not really sharp and therefore limited in usefulness.

Also, my (second) comment was not specifically about your comment but generally about the “vibe” of this community

I agree that the wording is a bit ambiguous, I interpreted it the way it seems more natural to me. In the post by the researcher(s) themselves, it says in the tldr paragraph that the “agent produces concrete, reproducible PoC inputs to confirm its findings” but also that they (probably humans) “explored the exploitability of the issues and developed a PoC demonstrating a RCE exploit primitive”. Apparently it finds the vulnerabilities very concretely but humans were involved for the full-blown exploit. It also doesn’t say much about the number of false-positives.

I’m not in the business, so I can’t tell how much of the work such agents are actually saving. Since the articles don’t say much about the amount of human involvement, the imagination conveyed by them probably depends strongly on the (knowledge of the) reader. But in my opinion it is a bit of stretch to say this is downplaying it. It should be noted though, that the article probably sources its information from a post by the company selling that AI.

With that information, the “without any confidence” and “area of interest” parts of your previous post still seem misleading.

CO2 emissions are a huge problem, of course. But it is not specific to AI. Data centers are starting to become a significant factor of energy consumption but I think it will stay very manageable compared to other consumers and given the utility it provides. And since data centers luckily natively require electricity, it is much easier, compared to e.g. transportation, to switch them to renewables. And renewables are very often already the cheapest source of energy anyways. So I think AI is just another thing that humans do that requires energy, and it comes with the same tradeoffs (the utility vs. the cost of sourcing that energy). So in my opinion we should mainly focus on accelerating the transition to green energy.

Here’s a good overview about AI carbon emissions I just found: https://www.carbonbrief.org/ai-five-charts-that-put-data-centre-energy-use-and-emissions-into-context/

I’m frankly quite annoyed by the amount and extend of anti-AI hate in this community. It almost seems like this is a pure anti-AI rage community. The capabilities and the utility of LLMs are basically always denied or downplayed as much as possible without running into obvious contradictions.

It would be so nice to have some differentiated and insightful discussions here, about what can or cannot be done with AI, positive and negative impacts it has, possible new use cases, how AI should or should not be used, how the overall benefits of AI can be maximized and the overall negative effects minimized, what the world with AI could be like in the future, …

In the article it says the ffmpeg vulns were found by an “autonomous” agent and that it produced a proof-of-concept for each. So what do you base your claims on? They seem quite contrary to that.

Even if there was still a lot of human work involved, it seems that the LLM-Agents can help a lot with security research, as the number of (real) zero-days that are beeing found recently (with the help of AI) seems to spike (telling from what I read, e.g. here on Lemmy, or the number of security updates for my distro).

OnlyOffice and therefore EuroOffice does not support ODF natively. It can only be converted to Micrososft’s OOXML for viewing or editing: https://helpcenter.onlyoffice.com/docs/userguides/document_editor/supportedformats.aspx

In the linked Nextcloud blogpost, the CEO of Nextcloud is quoted saying they would put full support of open standards like ODF “on top of the agenda” for the next release (after working on the desktop and mobile apps and integration features (maybe for this release)?).

OnlyOffice does not natively support ODF, only after conversion ODF files can be viewed and edited: https://helpcenter.onlyoffice.com/docs/userguides/document_editor/supportedformats.aspx The page doesn’t say anything about writing, so it may not be possible

This is a very simple mouse with no/hardcoded software (only registers for basic configuration): https://www.nager-it.de/en/maus

It has an “as fair as possible” supply chain and can also be self-assembled. Detailed documentation is here: https://www.nager-it.de/en/informationen/material

Democracy is supposed to ensure as good as possible that everyone’s interests are considered. For example those of the people affected by sewage, which might not affect the experts you’d like to be in control. Also, after what you wrote, I don’t trust you to judge who is an actual expert with good intentions to put in charge. And you likely don’t trust me with this either. So we should probably have the same say. And if the experts in charge would at some point be (as they already somewhat are) the CEOs of AI companies, you would probably also like to have a say, just as everyone else.

AI usage for this comment: DeepL and the translator in DuckDuckGo for spelling and translation, e.g. of “sewage” and “convulsing” (what the heck is this last half sentence you wrote there, btw?)

All of this is intelligence in my opinion. It may be far less intelligent than some human, but it still is (impressively, in my opinion) intelligent for a computer. Obviously, intelligence is very hard to define precisely. But LLMs can solve some nontrivial problems they have never seen before in that exact form and without existence of a clear algorithm to find a solution. And it even has some utility in many cases, as the comment describes. This is clearly intelligence. Even if it may not hold up to some promises made about them or people using it in inappropriate ways.

Btw., your original comment is very antidemocratic, as you demand to exclude groups of people from decisions, just because you don’t like what they think!

This (the keyboard thing) is is obviously false, so I have to assume the whole story is

I’ve last seen it last month. And I have an old chat, where FluffyChat and (“old”) Element show all messages by now, but Element X can’t decrypt many and both Elements report that they can’t guarantee the authenticity of many messages (even my own). For a long time, my chat partner could only read messages I sent via FluffyChat but not those sent by Element. I have not checked if that is still the case.