sjbzbeiks

Benchmarks they share are on the much older v4 of DSF. DSF V4.1 1017 is a big step up in benchmarks and is also actually twice as many parameters.

Anyway, I use DSF v4.1 on max as much as I use Opus 5.5 on xhigh, Opus is definitely a more versatile model, but I’m not getting any value using it to implement well defined tasks that DSF v4.1 does just as well at for a fraction of the cost.

You see where GLM-5.3 is in this test down but respectable, but this model benches below DSF 4.1. TLDR basically nothing in this benchmark invalidates the Deepseek that everyone is using today.

You vendor the deps

I lived through a city that did this and I myself do miss the night sky, but the reality is, it was believed to have spiked crime (hard to prove that when the entire country went through and increase but it is true that my city did have the worst drop in safety rankings), and many women coming home at night did report feeling less safe, so they’ve since reversed it. It is definitely one of the policies that contributed to the mayor of the city losing the next election (to be clear his successor reversed the policy the next day after winning)

I think is usually a symptom of how hard it is for the organization to do things, the technical side of this is not actually that hard.

I say this because I’ve gone through a few of these, some with monorepos (the easiest, search and replace and you’re done), some not (yes the hardest but you can just vendor).

At least in the situations I’ve faced this was genuinely not horrible beyond just the organization itself being complicated about the solution.

I mean … that would have large large costs when the Americans retaliate. I don’t think this is the easy call you claim it is for Europe.

Entirely depends on the work asked and the repo involved.

When I’m doing work on a repo where I’m implementing a standard and the agents have to read the standard to keep from hallucinating my usage skyrockets.

Hell this changes depending on which language I’m working with.

yeah I mean it just depends on time horizons, if you bought at 117k you are hurting now if you need the money ASAP.

Also, I gotta say I do not think Bitcoin is a bubble or whatever (IMO a real value there), but really this sort of site makes it seem like it is a bubble with the sort of "blind to history" boosterism.

Go read Reminiscences of a Stock Operator, or Market Wizards series, Extraordinary Popular Delusions and the Madness of Crowds, or any number of books about financial history and there are endless people saying 'it will never die and all the doubters are just wrong' before any big market crash.

I feel like im losing my mind a bit reading these responses, someone can at once be very hated and very loved, this is not a new thing, one does not invalidate the other.

Of course he has a lot of fans, he has a lot of hate too. That makes him a divisive figure by definition (I’d least hope we can agree on that).

I mean I guess we can disagree but it seems like common sense to me to want someone more neutral to be in charge of super mega important tech.

Maybe I’m the weird one nowadays as I tend to try and vote centrists for the same reason.

I mean like the original article, I gotta say, Tabs vs Spaces.

I just prefer TUIs, I think if you prefer GUIs you should very much use them and ask for more of them, but if you prefer TUIs please do use those too. I could go into all the reasons I prefer TUIs but this is a HN comment not a manifesto.

Please just use and develop what you prefer.

Tabs vs spaces.

I’ve always appreciated the positive side of TUIs and appreciated less the positive side of GUIs. I didn’t grow up with a computer at all and in one of my first adult jobs I had to use a TUI at Papa John’s for punching in orders, it was 20x faster than anything I used after it at other restaurants that were GUI driven (keyboard speed wins for me, fit my brain perfectly). I think I learned it in 5 minutes. I was just a normy trying to pay bills.

I dunno why we gotta be insulting to people’s preferences, the article is genuinely bad about this.

I think this is the issue others are having, when you say:

> when I can have it do something like write entire working kernel module fixes for old MacBooks on a whim

They’re not saying it can’t do that, and that’s not proof it doesn’t hallucinate. In fact, having used 6-8 agents at a time for a year plus while writing AI tooling for an AI startup, I can definitely surely tell you that they’re almost inversely correlated as in models that hallucinate a lot sometimes also put out the best most impressive solutions.

I’m definitely not anti AI and I definitely have found a way to make it work very well and I’m content with the work I get out of it (again maxing out several max 20x subs), but I have had sol definitely hallucinate this week and I’m a bit shocked you’re trying to say otherwise.

Listen I know it’s going to be I’m holding it wrong too, but I’ve been reading white papers and research on LLMs for a long time and was definitely at the cutting edge of context engineering, implementing features in our tooling harness a year before they were in codex or Claude.

maybe I am holding it wrong still but but like at some point if I’m holding it wrong who else will be holding it right? Dozens of people? At some point, the technology has to be approachable enough for everyone to have your point of view automatically.

This always sounds good on paper and this is very common lore, but then when you get into production escalations a very common problem is a lot of software depends on limits for autoconfiguration of thread pools and even several runtimes (go and java for example, at least .net is mentioned in the article), yes you can usually set them with a flag but people have to know this, communicate it, enforce it. Basically replace adhoc what limits is doing for you automatically configuration wise

So this just all assumes you have a setup where all teams communicate the necessary information perfectly.. what happens in practice is workloads degrade at edge cases because there are 256 threads running for a thread pool instead of 4.

You’re not totally wrong but I think the motivations are varied. Using myself as an example, I have paid huge sums for software, films, news, and yes open source software, but I hate paying 5 bucks for a sub or buying certain products because the deal just isn’t a fair trade. I’d say most modern software is a bad deal.

That said I am a cheap bastard.