Been running the same design prompts through GPT-5.6, Fable 5, and Grok 4.5 for the past few days and wasn't expecting the gap to be this obvious.. GPT-5.6 reasons like nothing else: → ask it why a layout works and you get an answer better than most actual designers could give you → ask it to just make something beautiful and it plays it safe → every output feels like it's showing its work instead of trusting its taste Fable 5 can genuinely produce great design, that's not the issue: → feels less like using a tool and more like negotiating with it → you end up doing math before every prompt instead of just designing Grok 4.5 just does the job: → prompt in, finished layout out → spacing, type, hierarchy, all of it already feels considered → saves you fifteen minutes usually lost nudging padding → it's sitting inside x premium, so there's basically no friction to start using it The best model isn't the one that produces the prettiest screenshot. It's the one that gets you from idea to production with the least friction. Right now that's grok 4.5, and it's not close.

Much of the Western geopolitical commentary still treats India, through an externally imposed lens and routinely underestimates the region’s contextual history. In turn, turning a blind eye towards the depth of India’s societal intolerance for terrorism. But you wouldn't get it.

Gotta add jev to the stack, immediately

If the white population experienced the racism Indians experience on a daily basis, the suicide rates in Western nations would rapidly deem entire nations obsolete. Fact: they're already dying merely due to mental health related issues. Not condoning hate, but yet they're obsessed with Indians? Interesting.

Reeling on Instagram and all of a sudden, someone says Hermes 👀 @NousResearch credit: @rolfv12

New job in tech, they asked whether I'd like to go for a windows pc or a macbook, which way we swinging fam?

DeepSeek V4.1 Flash has "comprehensively surpassed V4 Pro across all key metrics, including performance, cost, speed, and task completion time" It just doesn't stop 📈

Waited 5H for 12 minutes of deepwork using Astra @thsottiaux wen? 🫪

Grok Bot is very slick, beautiful interface but at the end of the day, Hermes edges out on just being able to 'do more' Its less of a polished package and more of a powerhouse, depends on what you're after I suppose

What are your experiences with the AppStore reviews? Be honest

I've got a ChatGPT, NousResearch and GrokBot sub, and I genuinely feel like I'm creating more value because of it. Wby?

As a Hermes power user, I really like the Grok Bot ui and would welcome more changes pointed towards minimalism on Hermes Maybe an easy and pro mode would be good?

Rockstar and GTA6 need to fail if we're to see gaming continue to evolve in a direction that consumers benefit from Digital only = absolute control over not just your reality but your virtual reality too Gaming won't be an "escape" any longer and I hope they aren't able to get away with this

the advantage of building every day is not the output it's that you stop needing motivation to trust yourself momentum gets less emotional once you've survived enough ordinary tuesdays

Realistically this bot trend is about to 20x your API costs for a marginal gain in efficiency

Haven't quite figured out how to use Hermes bot mode effectively, how are you using it within your workflows?

you know a product is good when people stop using it and start identifying with it

the piece that gets attention isn't the one with the most polish, it's the one you actually shipped while the polish was still missing attention rewards the visible attempt, not the finished thought

tibo vagueposting astra.. brother we are already seated just drop it