x509
97 posts
@richiemcilroy You are a goddamn sellout. They are using you. Anthropic will rug-pull at any moment, better get addicted to open models.
English
the Anthropic OSS program for Claude is fun, because I now get the Max plan for $0/mo, saving $200/mo
but I’m still being charged $200/mo and support won’t reply
great success
English
@litteralyme0 Shout out to bipolar disorder, gotta be my favorite mental illness
English
Very wrong, very dangerous
You want your APIs to do the exact same thing, every time
AI is great at many things; reproducibility is not one of them
Naval@naval
AIs replace UIs and APIs.
English
TUIs are not good sorry yall
a CLI is a utility, and situational. this should not be confused with stuffing a full interactive GUI into a low capability platform.
"lets ignore all the great UI technology of the last 20 years and build some caveman shit"
English
@MatthewBerman @thdxr China will win. The world's biggest dictator state is somehow leading the way for freedom of running local models.
English
@thdxr A strong US open source strategy is the answer to China’s current open source dominance. I don’t see how “more closed source” is the answer.
English
@yacinehmito @thdxr Also remember the letter bill gates published? Effectively encouraged anyone to stray away from free software movement at the time.
English
@thdxr It was mostly a Microsoft thing.
theregister.com/2000/07/31/ms_…
English
@pseudokid what's the best way to use all these? opencode?
English
Kimi K2.6 - frontend
Deepseek V4 Flash - cheapest all-rounder, cache king, 1M
Mimo V2.5 - excellent vision, 1M
Qwen 3.6 Plus, Mimo V2.5 Pro - decent all-rounders, 1M
MimiMax M2.7 - decent backup
All current gens are way better at using the terminal than their prev gen
Keith@gnukeith
Best Chinese model right now? I'm using Kimi K2.6 myself
English
@jaimandal_ @ThePrimeagen If you don't value your time, keep at it with the old way, old man.
English
@ThePrimeagen Spending hours trying to fix a bug -> giving up and going to bed -> dreaming of a fix -> waking up and trying it -> actually fixed the bug
Different type of happiness! AI is unfortunately taking that away.
English
I really just like to program
Hands on keyboard, music, deeply thinking and enjoying the process
English
@pvncher @banteg @ArtificialAnlys Bullshit. Deepseek is not lobotomized. Anthropic and OpenAI models have so much "safety" in them that they detoriate the output.
English
@banteg @ArtificialAnlys You can’t convince me that deepseek v4 or kimi 2.6 competes with gpt 5.2 or opus 4.5
Gpt 5.1 maybe, or sonnet 4.5.
English
saw some charts that show that show how the US increases the lead on frontier models, so i took the data from @ArtificialAnlys and plotted the frontier lead in months. the competition looks very fierce and the open source models are only 2 months behind.
English
OpenCode Go is practically unlimited with Deepseek V4 Flash
Even at max thinking, which is pretty decent, I'm spending ~2% of my monthly limits a day
At that pace, it's ~50 8h session days a month!
Double that to 16h a day, and it gives you 33.3 days making ~4%/day its ceiling
Lotto@LottoLabs
Update on Opencode Go It’s great value for $5/month, there’s really no reason not to do the first month. At $10/month it’s still good value and gets you access to all sota OS models. You can’t daily drive it without hitting limits on the big models but w/ Kimi x3 you won’t hit limits unless you’re insane. Overall highly recommend the first month, then make your own decision.
English
@pseudokid Ollama cloud has better limits, good for running bigger models (glm 5.1, deepseek v4 pro)
English
@zekramu @DaelonSuzuka Dude stop trying to sound edgy. You're literally contradicting yourself in every reply. Dumbass.
English
@DaelonSuzuka you don’t have to write a novel to understand it, but you do have to have good reading comprehension skills
English
you can outsource your work
but you cannot outsource your thinking & understanding
Austin Kennedy@astnkennedy
I'm 22 years old and Claude Code is deteriorating my brain. Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me. In convos with a couple of friends, it's been a point that's been brought up pretty frequently. None of us feel as sharp as we used to. I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot. P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless
English
@promptprincess None. They are just a means to an end, meant to do things faster.
English
@x509dot He would joke privately about covering up fixes for things reported to the security list:
English
A rich comment from the person single-handedly responsible for ~80+% of exploitable vulnerabilities in the kernel since 2011: news.ycombinator.com/item?id=479690…
English
@spendergrsec Wasn't it linus who started this stupid idea of obscuring the security fix commits?
English
Argument doesn't fly when 1) you take the private reports and 2) have taken over the CVE process. Can't both not believe in the kind of disclosure the rest of the world does and run the disclosure system at the same time.
English
Casual reminder that these posts are from american founders who can't sell your data and are salty because of it. The EU doesn't force you to put a cookie popup for functional cookies :)
Abide by my GDPR information deletion requests and stay mad.
Jonas Fröller@jonasfroeller
What if the EU built GitHub?
English
@astnkennedy just get your job done, and get sharp at doing other stuff with your free time. why some people have to take everything to "I need therapy" extremes.
English
I'm 22 years old and Claude Code is deteriorating my brain.
Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me.
In convos with a couple of friends, it's been a point that's been brought up pretty frequently.
None of us feel as sharp as we used to.
I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot.
P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless
English