I‘ d recommend playing around a bit with opencode and their free models, just to see what changed. Oh and you don’t have to use it to code, but a fun experiment would be to run it in a Linux container and see what it can do.
I‘ d recommend playing around a bit with opencode and their free models, just to see what changed. Oh and you don’t have to use it to code, but a fun experiment would be to run it in a Linux container and see what it can do.


Mentioning A.I. for programming on the fediverse and for the Linux Kernel no less? You’re heading in a world of pain my friend. Good luck!


Zum Mäuse melken aber auch!


From what I gather a different harness can make quite a difference. Seems like a model can work better or worse depending on the harness, that’s at least what I‘ve heard from the community.
A harness for coding is probably different from a harness for agentic tasks like Hermes or opencode. … probably it also helps if you don’t vibe code your harness with little or no supervision. (Cough, Claude Code, cough)


Interesting. I should have read the cloudflare article, not just linked it. Of course, anthropic does the bullshit it’s known for.
But I heard several security researchers experimenting with own harnesses. Seems to make quite a difference.


Cloudflare, for instance, shared that Mythos Preview was particularly adept at exploit chain construction, which is basically spotting how several bugs can be used to create a series of attacks that do more damage than a single exploited flaw.
But Anthropic also revealed that Mythos isn’t necessarily ready for primetime, which might also be part of why it’s actually keeping it to such a small and controlled base of users.
Cloudflare also noted that other models found a lot of the same bugs as Mythos—an observation that has been made elsewhere. A security company called Aisle tested several small, open-source models and was able to find the same vulnerabilities that Anthropic highlighted when it announced Mythos—vulnerabilities that went unnoticed by humans for decades.
My take is that Mythos is quite good, but is of course overhyped by Anthropic. Current models are quite capable now and experts can deploy them effectively. Good news is that a script-kiddie still will have a hart time to find and create workable exploits.


This is a question I keep asking myself about, well, the entire internet lately. “What if this all just doesn’t work this time?” What if AI companies can’t replace search? What if streaming video can’t replace Hollywood? What if short-form video apps can’t replace social media users? What if Silicon Valley can’t brute force their products — and ideology — onto the masses again? To take it even further, what if the dot com crash and the AI crash are actually part of the same 25 years epoch of technological stagnation? I’m not going to lie, I find this line of questioning exhilarating.
What if OP is high on drugs? What if he just strings a list of hot takes together that are getting more and more nonsensical? What if the only reason he talks about technological stagnation is because he still hasn’t his flying car yet?? What if a meteor kills us all tomorrow??? I‘m not going to lie, I find this line of questioning mindnumbingly boring.

deleted by creator
„Night Train to Lisbon“ by Pascal Mercier.


Man muss ja nicht immer den Brenner nehmen, gerade in den Ferien ist das doch reiner Masochismus.
Nehmt den Reschenpass und habt eine geruhsame Fahrt durch die wunderschöne Landschaft des Vinschgau.
Oder nehmt mal den Zug, auch schön!
No, hamster wheel.

Brought to you by the power of Destillation. But I actually don’t mind, so we’re getting at least somewhat open models.
Take that, flat earthers!!!
Vor kurzem hat hier auf Lemmy jemand den Comic „sexy losers“ verlinkt. Achtung NSFW:
https://www.sexylosers.com/comic/014/
Ehrlich gesagt, ich weiß nicht ob dafür jetzt up oder downvotes bekomme. Kam mir nur so in den Sinn bei diesem Thema…


Es ist eine unglaubliche Arroganz der “Bildungsverantwortlichen” das sie wirklich ernsthaft glauben das NUR und ERST ihr Unterricht dieses Verständnis von Ursache, Wirkung oder “logischem Denken” fördern können
„Nur“ und „erst“? Ich glaube du unterstellst hier nicht nur dem Artikel, sondern auch dem ganzen Bildungssystem etwas was so nicht stimmt.


Eine sehr nützliche Eigenschaft, solange die Sonne scheint. Und leider auch nicht auf die Minute genau. Aber auch wenn deshalb dein Kommentar wahrscheinlich ironisch war, ist es dennoch eine nützliche Fähigkeit zu jeder Tageszeit zu wissen wie spät es ungefähr ist.
Der Vergleich mit digitalen und analogen Uhren erschließt sich mir aber nicht. Eine (Quarz) Uhr mit analogen Zifferblatt zeigt die Uhrzeit genauso exakt an wie Ihr digitales Äquivalent. Es ist also nur die Art der Wiedergabe die anders ist. Aufgrund des eigenen (Mode) Geschmacks eine Art davon als veraltet darzustellen halte ich für Quatsch.


Ich misstraue Stimmen die aufgrund von persönlichen Meinungen und Anekdoten Dinge als antiquiert bezeichnen.
Also ich halte es für eine wichtige Fähigkeit die Zeit von analogen UND von digitalen Uhren abzulesen und es gibt in meiner Umgebung auch nicht weniger analoge als digitale Uhren.
Also ich finde die ja sympathisch in dem Video, aber im Prinzip ist das nur eine Marketingkampagne, die unterstreicht dass ihre vollmundige Vorhersage nicht eingetroffen ist.


It’s indeed important to be an understanding boss. And I’ve also been on both sides of this and agree with you that it sucks pretty much.
However: this guy is a bad worker with a bad attitude and clearly states that he has no interest in his job. He does bad enough work to upset his teammates. You’re his boss. Don’t hang out with him. Maybe a beer after work, but even that stretches it. You wanna be his friend and hang out with him outside of work? Then you both should not work directly with each other. There is a time and place for delicacy and sometimes not.
Sorry, I’m a bit harsh! But I had problems with a co-worker myself. And I suffered actually years from constant drama because I was polite and considerate and forgiving. And it would have saved me from so much frustration and stress if I kept my distance in the beginning or just plainly told him to fuck off.
I like the blog post for the most part. Seems like a nuanced opinion about A.I. Can’t really say much about the programming part - I’m not a programmer.