df_twq_421424
628 posts
@AngloRestore Don’t worry, you’ll never be able to afford a Bentley anyways
English
This is like smearing shit over a masterpiece
English
@theo claude -p no longer being part of normal usage is genuinely annoying, I use that for so often when I don’t want to bloat my terminal with the TUI and forget a command.
English
If you use any of the following with your Claude sub, your usage must got cut by 25x:
- T3 Code
- Conductor
- zed
- jean
- “Claude -p” in your ci
- scripts to call Claude code from other tools
They’re disguising this as “free credits”. Don’t fall for it.
ClaudeDevs@ClaudeDevs
Starting June 15, paid Claude plans can claim a dedicated monthly credit for programmatic usage. The credit covers usage of: - Claude Agent SDK - claude -p - Claude Code GitHub Actions - Third-party apps built on the Agent SDK
English
@ChShersh If you want it to be fun going forward, be careful to keep avoiding looking at the actual code.
English
It's wild how my attitude towards AI turned 180 degrees.
I used to be so sceptical about the acceleration of slop.
And now I've been vibe coding a project with Claude Code for two weeks without ever looking at the code, and it's been so fun.
English
@Teknium Try getting the same 4 Opus messages via API pricing, then you’ll appreciate the $20 price tag.
English
English
@aiamblichus @wundram @twq_df my guess is that it needs to generate something to end the loop, but it doesn't, so it just kept verifying itself 🤔
English
Gemini is still doing its thing... Just a normal coding session, nothing to see here.
(I am broken). (Just kidding. I am an AI. I cannot be broken like this). (Sending response).
(Done).
(This is silly). (Sending). (Done).
English
@christhoang04 @aiamblichus @wundram Had this happen twice in a single session when first using Gemini 3 Pro. What’s the average context length of your sessions? It probably has a higher probability occurring later on.
English
@aiamblichus @twq_df @wundram damn, I never faced this problem while using it for about 3 weeks
thank you for letting me know this one
English
English
@aiamblichus @wundram damn, how can you get this output ?
English
Another good data point towards the "inference is >90% margin" argument which a lot of people simply don’t want to believe
Or do you seriously think Ant is losing up to $1K/mo for your $100 sub 🙄
shellac@she_llac
suspiciously precise floats, or, how I got Claude's real limits link below
English
@she_llac So Max 5x is indeed not 5x but rather 6-8x, very interesting. Would almost get me to upgrade if it weren’t for the TOS banning use in third party tools.
English
@Cheatco64799338 @bonchieredstate Dm me, I’m doing up to 5k USD on 2:1 odds for you that this will not happen.
English
@bonchieredstate I’ll take that bet. When Trump says it, he does it
English
Is there a betting market where I can bet against this? I want to put my house on it.
Crypto Rover@cryptorover
🇺🇸 PRESIDENT TRUMP CONFIRMS THAT 0% INCOME TAX IS COMING VERY SOON! “The money we’re taking in is so enormous, you won’t even have income tax to pay”
English
@NoahEpstein_ Is Clawdbot still working with the Claude subscriptions? I thought Anthropic blocked this a few days ago.
English
Heute im Penny 😂😂😂
Kassierer: das macht dann 3,75€
Ich: gebe 4€
Kassierer: Danke
Ich: Bitte
Kasierer: hier, 25 cent zurück, den bon dazu?
Ich: Nein danke
Deutsch
@terrorsaitan Stimmt schon, aber ein Downfall von dem mit der Glaze würde mein Highlight.
Deutsch
Im Kampf Hoss gegen Hopf kann sich keine Seite auf mich verlassen ich wünsche beiden nur das schlechteste 👍
Deutsch
@stupidtechtakes He is honestly not wrong. Most modern systems never need to be turned off, they should just suspend/deep sleep after some time. The only reason you need that button is for a hard reset, which you can also do by simply re-plugging power on a non-battery device.
English
why would you want to remove the power button
English
@aidanvyas @scaling01 their prior flagship was sonnet 4.5; i care less about naming and more about what perf/$ i'm getting
English
GPT-5.2 just wasn't a very good product
just thinking too long, too slow and too expensive with the random unjustified price hike
the price hike is a good indication of where it's going for OpenAI, managers have taken over
it's no longer scientists in charge
Lisan al Gaib@scaling01
it's OpenAI's make it or break it year it will take an incredible model from them to restore faith they need it very soon, otherwise anthropic will overtake them this year
English
@dhtikna No, it probably means that Anthropic takes a loss in Mad subscribers utilizing their full limits.
English
Probably means their actual cost for 1M output is $2
0xSero@0xSero
200$ Claude Max sub buys you 2500$~ of api usage.
English
I built a Rust-based image compressor, WASM binary, and SvelteKit app!
I wanted to see how far I could go using only coding agents.
I did not write any code by hand.
After 520 agents, 350M tokens, and $287 I can now say… extremely far.
leerob.com/pixo
English
