Paul Kim retweeted
Replying to @theo
I'd recommend paying closer attention to what you post.
It's right there on the chart you're quoting. 100% is launch power. 90% to 110% is normal variance. The post says Opus 5.5 is inside that range and not a nerf.
You're quick to bash me because you don't like seeing others succeed.
Read how NerfBench works before you call it misinformation.
It's obvious you didn't look into it in the first place.
bridgebench.ai/blog/how-nerf…
Paul Kim retweeted
Replying to @paulbkimdev @ryanflorence
😂 You and all other other angry responses are proving his point! God you guys are so soft. Devs in tech are notoriously arrogant. Sure it's not every dev, but it is a very, very large percentage. Most spoiled group of workers I've ever encountered.
It has been very satisfying to watch dev egos not only get shattered, but to see existential dread take over, the same dread they were so happy to watch take over artists, writers, and everyone else who's work AI has threatened.
Paul Kim retweeted
If you understand your whole codebase, the codebase isn't that important.
Real software is larger than what your brain can comprehend.
Replying to @tobi
Hi Tobi, thanks for the feedback! We are working on making Claude Code more hackable, which will include being able to easily use Agents.MD or make other system prompt modifications. I’ll share more here when it’s ready to roll out.
Our reasoning for this was that we don't think that model families are interchangeable and the system prompt can have a big impact on performance.
I wrote here: teapawt.net/trq212/status/20807109… on how Claude models like their skills, system prompt, Claude.MD, etc to be formatted. In Claude Code we have different system prompts per model.
That said, I know this is a lot of upkeep and not worth the squeeze for everyone. Feedback heard and I'll keep you posted.
In the immediate term, you can always @Agents.MD from your Claude.MD.
Paul Kim retweeted
Elon @elonmusk try @OmarchyLinux!
Retweet please!
Paul Kim retweeted
j’ai mon abo supergrok grâce à x premium+
du coup je peux même pas profiter de l’offre de zinzin pour supergrok heavy, 99$ au lieu de 300$ par mois pendant 6 mois
je suis puni parce que je paie déjà
j’ai contacté le support pour voir s’ils peuvent me faire un petit truc mdr
Paul Kim retweeted
OKEY GUYS, YOU HAVE VERY LITTLE HOURS TO DO THIS BEFORE IT STOP EXISTING.
How to trigger SuperGrok Heavy $99 promo for 3 months on any account with no current plan.
1) Login into grok.com
2) Go to this url to buy SuperGrok for 15$ for 2 months promo
grok.com/supergrok/targeted-…
3) Now go to this url to get SuperGrok Heavy for $99 for 3 months
grok.com/supergrok/targeted-…
THIS WORKS 100% OF TIMES ON NEW/OLD ACCOUNT WITH NO CURRENT PLAN ONLY.
We didn't test on accounts with current plans, if you try it, let us know (:
NOTE: Do not worry, the price is deducted so at the end is $99 not 15+99.
If you didn't recieve the SuperGrok Heavy at $99 promo and still want to give Grok 4.6 a try, we found this working promotional url.
SuperGrok for $15 (50% discount) for 2 months.
grok.com/supergrok/targeted-…
Every game world you've ever played in was built by someone before you arrived.
Every room, every character, every possible outcome -- designed in advance, waiting for you to discover it.
We think that's about to change.
PixVerse Game is here.
RT + Follow + Reply = 300 Creds & Early Access in DMs (72H ONLY)















