@cloanix: found a wheelchair mod #foru #nichetok #edit #skyrim #elderscrolls

Cloanix

Open In TikTok:

Region: GB

Saturday 29 August 2026 01:31:09 GMT

174185

25039

207

8437

Music

Download

No Watermark .mp4 (7.79MB) No Watermark(HD) .mp4 (7.2MB) Watermark .mp4 (7.98MB) Music .mp3

Comments

ethan 𓅓 :

Is high hrothgar wheelchair accessible

2026-08-29 15:22:22

1836

nav_hanma :

What mfs will do instead of playing morrowind

2026-08-29 01:37:51

1349

Fil :

Dragonborn the boneless

2026-08-29 05:17:55

2831

pyrit :

ngl I'm a wheelchair user, i want this so bad

2026-08-29 09:51:43

429

beep :

Kinda fucked up how much of a lack of wheelchair accessibility there is in Skyrim. Like, imagine if the dragonborn was a paraplegic. Everyone's fucked and Alduin wins cause we cant get to high hrothgar. Imagine trying to take a wheelchair up the 7,000 steps. Someone needs to get on the greybeards about that, cause that shit is not ADA compliant.

2026-08-29 17:55:18

124

Joseph Abalos :

If Bran Stark was in Skyrim lol

2026-08-29 21:36:01

0

nexey :

By the nines I'm geeked

2026-08-29 11:26:32

536

. :

That's what happens when you don't get a sequel for 15 fucking years...

2026-08-29 13:34:40

93

KC :

Not only do I have to start a new file now thanks but I need this mod 🤣😂

2026-08-29 21:26:30

0

BRIAN Oz :

Proof you have 500+ hours Skyrim 🤣🤣🤣🤣

2026-08-29 21:44:06

0

Astrogothe :

Great now we’re gonna get 15 new anyaustin videos to see if different cities in Tamriel are ADA compliant

2026-08-29 16:29:34

41

Hunter :

WHITERUN is NOT wheelchair accessible

2026-08-29 16:19:18

9

SOMBER44 :

when you use whirlwind sprint

2026-08-29 21:23:39

1

BjornOnTheCob :

is the way to Sovengarde dragon born accessible

2026-08-29 12:11:06

140

Le Studio D’Allamax :

Dodo Bizarre Adventure

2026-08-29 13:47:16

24

wambofr :

Skyrim x guilt trip

2026-08-29 09:51:42

52

willweiler :

kickflip?

2026-08-29 16:17:06

0

Salvador :

How are you going to climb the 7,000-step staircase?

2026-08-29 18:24:25

6

yogihalo :

the elder scroll V steel ball run

2026-08-29 10:50:27

47

darthy555 :

You gonna have a lot of trouble with the 7,000 steps

2026-08-29 16:40:28

16

mychillalterego :

We got inclusive Skyrim before ES6

2026-08-29 14:03:48

5

IM IGOR :

By the 9 he’s whipping that stead 🗣

2026-08-29 14:59:06

7

kalobbenafield :

whirlwind sprint should change to whirlwind roll or sum

2026-08-29 15:42:50

9

To see more videos from user @cloanix, please go to the Tikwm homepage.

Other Videos

Lara raj hootie fruitti scenepack katseye #fyp #fypviral #kpop #katseye #dontflop

Lara raj hootie fruitti scenepack katseye #fyp #fypviral #kpop #katseye #dontflop

#وستنا_جيتك_يعيوني🥺💔 #ستوريات_حب🥺💘 #غرامو_لحمصيه🤍

#وستنا_جيتك_يعيوني🥺💔 #ستوريات_حب🥺💘 #غرامو_لحمصيه🤍

#michaelmyers #halloweenshirt #graphictees #fyp #viral

#michaelmyers #halloweenshirt #graphictees #fyp #viral

#foryoupage #fyp #kuwait

#foryoupage #fyp #kuwait

That’s the idea behind a self-improving AI agent. Not a system that magically rewrites itself overnight, but one that captures what happened, measures the result, reflects on what worked, identifies what failed, tests better approaches and keeps the strongest version. 🔁 ⚙️ The real power is in the loop. First, the agent performs the task. ▶️ Then it records the inputs, actions, context and output so every run becomes useful data instead of disappearing into chat history. 📊 Next, it measures performance against clear criteria such as accuracy, quality, completion rate, error count, cost or speed. Without metrics, “better” is just a guess. 🔍 Then comes reflection. A review or critic layer can inspect the result and ask: What worked? What failed? Why did it fail? What should change next time? 🧩 Over time, repeated failures can be grouped into patterns. Maybe the prompt needs more context. Maybe the workflow is missing a step. Maybe the memory needs improving. Maybe a tool call is unreliable. Maybe the agent needs stricter rules. 🚀 That feedback can then be turned into a better version of the agent. But this is where good engineering matters. You don’t just deploy every change. 🧪 You test it first. Compare the old version against the new one using the same evaluation criteria. If the new version genuinely performs better, keep it. If it performs worse, roll it back. If the results are unclear, keep testing. ✅ A practical improvement cycle looks like this: Do → Measure → Reflect → Improve → Test → Deploy → Monitor → Learn → Repeat 🔄 The system keeps moving through the loop, but every improvement should be based on evidence. To build something like this, you need a few core components working together: an LLM or agent brain, task execution, memory, evaluation metrics, a review layer, an improvement process, a safe testing environment, deployment controls and monitoring. 🧠💾📈 The goal is not to create an AI that operates without limits. 🔐 The goal is to build a controlled system that becomes more reliable because it learns from evidence, feedback and previous results. Start small. Pick one repeatable task. Log every run. Define what success looks like. Review failures and wins. Version your changes. Test before deployment. Then keep feeding the loop. 📈 Small improvements compound. If you’re building AI automations, support agents, research workflows, internal tools, content systems or business processes, this is one of the most useful AI architectures to understand right now. 💾 Save this for your next AI build. 🤖 Follow TechSerks for more practical AI systems, automation and agent workflows. #TechSerks #AI #AIAgents #Automation #artificialintelligence

That’s the idea behind a self-improving AI agent. Not a system that magically rewrites itself overnight, but one that captures what happened, measures the result, reflects on what worked, identifies what failed, tests better approaches and keeps the strongest version. 🔁 ⚙️ The real power is in the loop. First, the agent performs the task. ▶️ Then it records the inputs, actions, context and output so every run becomes useful data instead of disappearing into chat history. 📊 Next, it measures performance against clear criteria such as accuracy, quality, completion rate, error count, cost or speed. Without metrics, “better” is just a guess. 🔍 Then comes reflection. A review or critic layer can inspect the result and ask: What worked? What failed? Why did it fail? What should change next time? 🧩 Over time, repeated failures can be grouped into patterns. Maybe the prompt needs more context. Maybe the workflow is missing a step. Maybe the memory needs improving. Maybe a tool call is unreliable. Maybe the agent needs stricter rules. 🚀 That feedback can then be turned into a better version of the agent. But this is where good engineering matters. You don’t just deploy every change. 🧪 You test it first. Compare the old version against the new one using the same evaluation criteria. If the new version genuinely performs better, keep it. If it performs worse, roll it back. If the results are unclear, keep testing. ✅ A practical improvement cycle looks like this: Do → Measure → Reflect → Improve → Test → Deploy → Monitor → Learn → Repeat 🔄 The system keeps moving through the loop, but every improvement should be based on evidence. To build something like this, you need a few core components working together: an LLM or agent brain, task execution, memory, evaluation metrics, a review layer, an improvement process, a safe testing environment, deployment controls and monitoring. 🧠💾📈 The goal is not to create an AI that operates without limits. 🔐 The goal is to build a controlled system that becomes more reliable because it learns from evidence, feedback and previous results. Start small. Pick one repeatable task. Log every run. Define what success looks like. Review failures and wins. Version your changes. Test before deployment. Then keep feeding the loop. 📈 Small improvements compound. If you’re building AI automations, support agents, research workflows, internal tools, content systems or business processes, this is one of the most useful AI architectures to understand right now. 💾 Save this for your next AI build. 🤖 Follow TechSerks for more practical AI systems, automation and agent workflows. #TechSerks #AI #AIAgents #Automation #artificialintelligence

#animals #nature #bird #owl #owls

#animals #nature #bird #owl #owls

About

Robot
API

Legal

Privacy Policy