23 • AI-pilled Founder & Designer • @resumeguruai @KRNLStudio @cubekrnl Tools shipped (includes oss) VaultOS • KRNL OS • ClipBubble • Update-pls

You gotta follow
Joined November 2014
Pinned Tweet
Meet KRNL Studio. @KRNLStudio ♥️
3
1
18
5,652
Since Fable 5.5 prolly isn't launching this week, I'm burning my entire usage. No point in preserving.
1
1
8
677
The concept of a parent thread, which manages all your other work, is a super easy but main setup I would prefer. If you have more than 3 threads running, and those threads have spun up their own subagents, that’s a lot of work to keep an eye on. A parent thread where you come to manage all permissions, status, and updates is very useful!
55
Don’t worry guys Fable 5.5 will come in to save us all
6
446
I wanted to convey that our current SOTA models would be antique in 6 months. But mf Gemini bashing took over lmaoo 😂😂
Opus 5.5 is still the dumbest AI will ever be from here on. Btw.
4
185
I asked Claude to swear, and now it actually does. This is beautiful.
1
3
93
Thanks Opus 💀 I’m going to be spending a lot of time on security today. Prolly also going to get into the OpenAI daybreak program if I can.
3
153
After the HF attack, we now have the Railway attack. It is happening. Vercel, Supabase & Cloudflare Pls have your shit together so that I don’t go broke
3
273
GPT 6.1 Sol on Cube Arena absolutely destroys GPT 6 Sol. Low on 6.1 Sol performs better than Max on 6 Sol.
GPT-6.1-Sol at low beat GPT-6-Sol at max. For under $1. $0.91 vs $4.63. Less than a fifth of the price, 6.1 more points. Head to head at every effort, 6.1-Sol vs 6-Sol: > low: 29.0 vs 9.6 ($0.91 vs $0.25) > medium: 30.5 vs 14.5 ($0.87 vs $0.58) > high: 35.0 vs 14.5 ($2.27 vs $1.36) > xhigh: 56.0 vs 19.6 ($4.06 vs $3.94) > max: 43.0 vs 22.9 ($4.71 vs $4.63) 5 for 5. Clean sweep. xhigh is the peak: 56.0 and #4 on the Fast v3 Index, behind Claude Sonnet 5.5 (59.0) and ahead of Claude Opus 5 (35.0). Budget pick is medium: 30.5 for $0.87, cheaper than low and still above 6-Sol's best.
2
2
430
Shoutout to @AdamHoltererer for contributing!
1
25
Claude is getting its own Bot & Dot version, called Claude Duet. Research preview. Pro & Max users both get access. Shame it's only available for US users to apply.
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
3
15
750
Extremely random but I’m pretty sure some of you have 3D printers and have been going crazy with Opus & Astra and making cool shit.
2
64
Opus 5.5 is still the dumbest AI will ever be from here on. Btw.
12
1
1
35
4,539
Nope, I’m not calling Opus 5.5 dumb. Read my post again.
1
252
Lol I didn't check for 24 hours and now I have 12 updates waiting for me across both devices. Thank god I made this so that I never have to do this manually again.
3
9
529
Grok Bot’s mobile responsive interface is what makes it sooo addictive. Also, the Group chats are a fucking game changer. I’m enjoying it so much.
1
4
203
Look guys I’m a prompt engineer..
Oh god, Claude’s classifier and auto-mode are exhausting. I’m gonna build a mod to fix this. If it works, I’ll make it publicly available.
1
4
319
It didn’t even ban me for saying sexy yayy
25
Oh god, Claude’s classifier and auto-mode are exhausting. I’m gonna build a mod to fix this. If it works, I’ll make it publicly available.
2
1
4
578
People who have an incorrect opinion are okay. It’s the ones who are confidently wrong that are extremely infuriating to talk to. Neither will they concede, nor accept a contradictory viewpoint.
1
1
137
Also pretty sure some sad sap will find a way to disagree with me on this tweet as well.
14