Latter question: it's 92kWh, which is not unreasonable even if it's twice what some entry level cars are being sold with.
Deep dive on the pack: https://www.batterydesign.net/byd-blade-2-0-compared-to-1-0/ ; it seems they've done some good old fashioned mechanical engineering to minimize the "not cells" part of the battery while keeping the liquid cooling effective.
Cost in Europe: based on past cars .. maybe 50-100% more? Higher taxes AND higher margins.
I can find the previous Seal at £46k for the premium spec version (390kW / 83kWh): https://www.arnoldclark.com/new-cars/byd/seal/390kw-excellen... , or you can lease it for £321. UK leasing seems to be the last place it's possible to get an actual beat the market deal, which is odd.
I get what your saying, but this is resonating with me and making me feel for the author:
Cursor: we have top notch safeguards for destructive operations, you have our guarantee, we are the best
Author: uses their tools expecting their guarantees to be true (I would expect them to have a confirmation before destructive operation outside their prompt, as a coded system guardrail)
Cursor AI: Does destructive operation without asking
Author: feels betrayed.
So yeah, I think the author is right because they trusted Cursor to have better system guardrails, they didn't (agents shouldn't be able to delete a volume without having a meta-guardrail outside the prompt). Now the author knows and so do we: even if companies say they have good guardrails, never trust them. If it's not your code, you have no guarantees.
Sorry - still author's fault. They didn't understand how LLM's work. They thought Cursor implemented some magic "I control every action LLM takes" thing. It's impossible.
right. But cursor _said_ they had some magic. At some point you have to trust vendors. I don't know exactly how AWS guarantees eleven nines of durability on S3. But I sure hope that they do.
Here is what they say, at the very top they explain that llm's are inherently unreliable. It looks like they offer security tools and safeguards, but they also provide an auto run option. There is nothing a vendor can really be responsible for someone shooting themselves in the face. You can argue that they shouldn't provide that, but that's what people want, so they do, with warnings.
It sounds like this user either didn't use security controls, approved prompts they didn't understand, or disabled the checks entirely. Working in IT/tech a big chunk of my life so far and seeing all the dumb crap people who even know better do, I would bet my house on that being the most likely scenario rather than cursor somehow being at fault here.
yeah and when you interview the junior dev who also convinces you they're smart and have something special, they also delete prod and guess what... not that devs fault.
You absolutely do not. When someone makes an unbelievable claim, such as having magic guardrails for LLMs that prevent dangerous actions (what would that even mean?!), you don’t have to trust that claim.
If you trust someone’s claim without justification, that’s on you.
> At some point you have to trust vendors. I don't know exactly how AWS guarantees eleven nines of durability on S3. But I sure hope that they do.
Trust is earned, it's built on reputations at the individual, corporate, and industry-wide levels. AWS has 20 years of reputation on which I can judge the value of their promises.
Not only has the LLM industry (it is not "AI" and never will be) absolutely not earned anything like that level of trust, the thing the technology has proven most effective at is in fact scamming. Making up something that looks/sounds convincing, especially if you aren't thinking too hard about it, is what they're best at. Combine that with a lot of money flying around and trust levels should be somewhere around "Elon Musk promises".
At this point there have been so many blatant examples of why you should never give a LLM "agent" control over production systems, but the allure of just giving some vague direction to a chatbot and telling it not to screw things up it just irresistible to some like Sideshow Bob stepping on rakes [1].
If everyone around you is whacking themselves in the face with the rake, and you know you can avoid it just by using your brain and not stepping on the rake, and avoid entirely by just keeping your rakes contained, but a rake vendor comes to you saying that instead they have built a new rake that they swear won't whack you in the face even if you leave it right in your walking path, do you trust them?
Yeah I wasn't clear with "the author is right", I think they are right to be frustrated, but that doesn't clear their own fault in the matter
It's just that it wasn't their fault alone.
This is not a polarizing issue, it's not just the authors fault, or cursors fault, or society's fault. It's everyone's, and we all got something to learn from this.
You just have to add a human in the loop for destructive calls.
Add an additional TOTP parameter to destructive calls that's generated from the agent UI that requires a human to click a button, which generates a code that's sent to the model and used in the call.
Having said that - even categorisation of destructive and non destructive calls is inherently not safe, unless you have very strict os level / VM like setup (everything read only, world access is through MCPs so it is not LLM deciding the destructive calls but the MCP etc. )
Sure, if you are ok walking around with a card.
I've been "walletless" for the past 6 years or so, and I don't want to go back.
Leaving and coming back home and only have to mentally track one object that I can't forget is great. If it breaks, I'll temporarily use cards or physical money until I get a new phone and install everything again.
"Use a card" is not really a good alternative for those that prefer not to use them. Sure it works for you, but not everyone has your preferences of walking around with a wallet.
Strange comparison. If you just call, text and check on bank apps, then the market is not for you. Just buy a used phone from 10 years ago.
It's like saying why should you get a new gaming laptop to replace your 6 year old current gaming laptop, when all you do is office work. If all you do is office work, why buy a gaming laptop at all? Just use a standard okish smartphone or tablet.
Who are these phones even for? I see people out in public and all they do with their phone is scroll instagram reels or ticktock. They need all this horsepower for that? I don't think so either. This is why I brought up fortnight because gaming is one example where there probably is a marked difference in frames per second between models. But 99% of people are probably just looking at images and videos and text on their smartphone, pretty low stakes stuff.
Strange attack on a very valid point. An extremely small segment goes outside the regular phone/social media/video space that actually uses these faster chips. For others the experience haven't gotten better relative to the faster hardware. Where are those cycles going?
reply