J A Z I I's banner
J A Z I I's profile picture

J A Z I I

@notjazii • 12,790 subscribers

CS Graduate 26 | Covering AI & Tech | Testing AI models | Building https://t.co/HQWNYNHAUc

Shorts

omg xiaomi cooked hard with mimo 2.6 this model is literally made for everything and it feels like the k3 moment again just look at this game output, it's crazy good too late for me to test it properly rn, so i’ll run my tests in the morning huge win for xiaomi here, they mogged everyone

omg xiaomi cooked hard with mimo 2.6 this model is literally made for everything and it feels like the k3 moment again just look at this game output, it's crazy good too late for me to test it properly rn, so i’ll run my tests in the morning huge win for xiaomi here, they mogged everyone

80,095 görüntüleme

Kimi K3.1 drawing Gojo in SVG asked model to make me svg of satoru gojo with reference and give me final output with bg music of it's own choice after about an hour of working it came back with this and cooked really harder

Kimi K3.1 drawing Gojo in SVG asked model to make me svg of satoru gojo with reference and give me final output with bg music of it's own choice after about an hour of working it came back with this and cooked really harder

25,527 görüntüleme

haiku 5.5 vs deepseek v4.1 flash tested both models with same prompt at highest reasoning available > haiku took 90 mins and cost $3.4 via claude code > v4.1 flash took 50 mins and cost $0.67 via aihubmix api haiku failed to make the game on the first try cuz of claude code bug, then spent over 30 mins just thinking on second try which one did better here?

haiku 5.5 vs deepseek v4.1 flash tested both models with same prompt at highest reasoning available > haiku took 90 mins and cost $3.4 via claude code > v4.1 flash took 50 mins and cost $0.67 via aihubmix api haiku failed to make the game on the first try cuz of claude code bug, then spent over 30 mins just thinking on second try which one did better here?

23,010 görüntüleme

Gemini 4 argon drawing Frieren in SVG asked model to make me an svg of frieren with a reference and give me final output with bg music too > took 1 hour 27 mins > used ~26.35M tokens > cost $5.19 in devin and here's the output it made, you guys decide if it cooked or nah

Gemini 4 argon drawing Frieren in SVG asked model to make me an svg of frieren with a reference and give me final output with bg music too > took 1 hour 27 mins > used ~26.35M tokens > cost $5.19 in devin and here's the output it made, you guys decide if it cooked or nah

19,290 görüntüleme

Fable 5.1 vs GPT 5.6 Sol tested both models with same prompt at highest reasoning available > Fable took 10 minutes to complete this test and costed $1.6 > Sol took 7 minutes and costed around $.95 even tho sol is cheaper and faster but results are really different which one won here?

Fable 5.1 vs GPT 5.6 Sol tested both models with same prompt at highest reasoning available > Fable took 10 minutes to complete this test and costed $1.6 > Sol took 7 minutes and costed around $.95 even tho sol is cheaper and faster but results are really different which one won here?

41,089 görüntüleme

DeepSeek V4 Flash vs GPT-5.6 Luna tested both models with the same prompt on highest reasoning > luna one shotted everything in under 3 mins in devin > v4 Flash needed an extra prompt to fix the movement and took over 5 mins in aihubmix cli which one do you think won?

DeepSeek V4 Flash vs GPT-5.6 Luna tested both models with the same prompt on highest reasoning > luna one shotted everything in under 3 mins in devin > v4 Flash needed an extra prompt to fix the movement and took over 5 mins in aihubmix cli which one do you think won?

47,729 görüntüleme

who is behind space bunny? it’s been a week since this stealth model went live and been testing it daily. compared to day one, it’s now: > way faster > giving way better outputs > still free for now opencode extended it for another week and looks like latest checkpoint got huge update you can make animations like opus 5.5 with space bunny now and made this one with it, not bad for a free model i think official model will drop next week, but still can’t figure out who is behind it lmaoo

who is behind space bunny? it’s been a week since this stealth model went live and been testing it daily. compared to day one, it’s now: > way faster > giving way better outputs > still free for now opencode extended it for another week and looks like latest checkpoint got huge update you can make animations like opus 5.5 with space bunny now and made this one with it, not bad for a free model i think official model will drop next week, but still can’t figure out who is behind it lmaoo

18,777 görüntüleme

asked opus 5.5 to add animations 5 hours later, here's where it ended up. tried almost everything but it kept breaking the character and animations so i stopped working on it and made cozy lantern hallow instead, which is fully open source now try it now: for zombie game i need help. how should i fix this?

asked opus 5.5 to add animations 5 hours later, here's where it ended up. tried almost everything but it kept breaking the character and animations so i stopped working on it and made cozy lantern hallow instead, which is fully open source now try it now: for zombie game i need help. how should i fix this?

13,419 görüntüleme

Grok vs Composer 2.5 Cursor just got acquired by SpaceX, so i wanted to test how good their own model is > both were given the same prompt > both completed the task around the same time too but the results are very different who do you think won?

Grok vs Composer 2.5 Cursor just got acquired by SpaceX, so i wanted to test how good their own model is > both were given the same prompt > both completed the task around the same time too but the results are very different who do you think won?

45,176 görüntüleme

Gemini 4 argon vs GPT 6.1 sol both models were tested with same prompt but results came out really different > sol was tested by me in devin cloud at default reasoning > gemini was tested by lentils earlier this month on pre release checkpoint argon isn’t publicly available yet, so can’t say how good offical checkpoint is, but this one looks pretty good already which one did better?

Gemini 4 argon vs GPT 6.1 sol both models were tested with same prompt but results came out really different > sol was tested by me in devin cloud at default reasoning > gemini was tested by lentils earlier this month on pre release checkpoint argon isn’t publicly available yet, so can’t say how good offical checkpoint is, but this one looks pretty good already which one did better?

14,442 görüntüleme

Opus 5 is soo good at 3D this has to be the craziest 3D output i’ve seen from any model looks like anthropic saw Kimi leading in frontend and 3D and went all in only problem is it’s still token hungry and slow as ass what do you think?

Opus 5 is soo good at 3D this has to be the craziest 3D output i’ve seen from any model looks like anthropic saw Kimi leading in frontend and 3D and went all in only problem is it’s still token hungry and slow as ass what do you think?

32,468 görüntüleme

Breaking: Fable 5.1 first output is here anthropic really cooked harder with this one and frontend is improved alot too looks like team is planning to release this anytime soon for some users fable 5 is being routed to 5.1 so check if you have access or not

Breaking: Fable 5.1 first output is here anthropic really cooked harder with this one and frontend is improved alot too looks like team is planning to release this anytime soon for some users fable 5 is being routed to 5.1 so check if you have access or not

19,586 görüntüleme

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

fable 5.5: combat animation at this point you can ask this model to do anything and it'll do it. there is no limit i just hope anthropic releases model this week
0:30
notjazii's profile picture

fable 5.5: combat animation at this point you can ask this model to do anything and it'll do it. there is no limit i just hope anthropic releases model this week

J A Z I I

154,280 görüntüleme • 4 gün önce

fable 5.5 is about to mog everyone asked it to make an animation that makes me feel like it’s agi and in about an hour it cooked this is made with pure code, no external assets used. anthropic really went all with this one watch till the end cuz it gets so good
4:22
notjazii's profile picture

fable 5.5 is about to mog everyone asked it to make an animation that makes me feel like it’s agi and in about an hour it cooked this is made with pure code, no external assets used. anthropic really went all with this one watch till the end cuz it gets so good

J A Z I I

93,103 görüntüleme • 4 gün önce

fable 5.5: bike on pelican after seeing some banger outputs from fable 5.5 i don't think astra 6.2 have any chance nov is gonna be super got. you guys aren't ready
0:26
notjazii's profile picture

fable 5.5: bike on pelican after seeing some banger outputs from fable 5.5 i don't think astra 6.2 have any chance nov is gonna be super got. you guys aren't ready

J A Z I I

62,776 görüntüleme • 5 gün önce

fable 5.5: birth of life tree animation no idea when anthropic is gonna release this model but with each checkpoint it keeps getting better and better model one shotted this animation with pure code in about an hour
0:30
notjazii's profile picture

fable 5.5: birth of life tree animation no idea when anthropic is gonna release this model but with each checkpoint it keeps getting better and better model one shotted this animation with pure code in about an hour

J A Z I I

28,813 görüntüleme • 2 gün önce

GPT 6.1 Sol is cooking asked model to add skateboarding to GTA V and this is what it made in 4 hours it’s still working, but all of this was done with 6.1 sol max and barely used any limits team really cooked harder with this model we now have a model with astra level intelligence at a fraction of the cost
0:51
notjazii's profile picture

GPT 6.1 Sol is cooking asked model to add skateboarding to GTA V and this is what it made in 4 hours it’s still working, but all of this was done with 6.1 sol max and barely used any limits team really cooked harder with this model we now have a model with astra level intelligence at a fraction of the cost

J A Z I I

252,567 görüntüleme • 1 ay önce

fable 5.5 vs opus 5.5 tested both with same prompt and let them pick style they wanna go with and fable clearly mogged opus in every way
0:35
notjazii's profile picture

fable 5.5 vs opus 5.5 tested both with same prompt and let them pick style they wanna go with and fable clearly mogged opus in every way

J A Z I I

30,933 görüntüleme • 5 gün önce

there is no way this is real tested astra and deepseek v4.1-1017 flash with same prompt at highest reasoning and results really surprised me > astra took 20 mins and cost $7 > deepseek took 1 hour 40 mins and cost $0.9 astra got details really well and made something more original than usual gpt outputs deepseek focused more on environment and it looks so good, but the koi fish aren't that great which one do you think won this comparison?
0:32
notjazii's profile picture

there is no way this is real tested astra and deepseek v4.1-1017 flash with same prompt at highest reasoning and results really surprised me > astra took 20 mins and cost $7 > deepseek took 1 hour 40 mins and cost $0.9 astra got details really well and made something more original than usual gpt outputs deepseek focused more on environment and it looks so good, but the koi fish aren't that great which one do you think won this comparison?

J A Z I I

90,885 görüntüleme • 20 gün önce

omg fable 5.2 is just too good asked it to create brawl stars clone and it gave me this after an hour everything was made using pure code with threejs and just look at the details, crazy good anthropic is coming for all game devs with its new models
0:56
notjazii's profile picture

omg fable 5.2 is just too good asked it to create brawl stars clone and it gave me this after an hour everything was made using pure code with threejs and just look at the details, crazy good anthropic is coming for all game devs with its new models

J A Z I I

156,515 görüntüleme • 1 ay önce

opus 5 is getting routed to opus 5.2 tested opus 5 on xhigh with the same prompt in devin and claude code but results came out really different > claude code one is clean and more detailed > while devin one is almost there but not the same opus 5 in cc used to be lazy and hard to communicate with, but something changed in the last 2 days now it works for longer and is way easier to communicate with anthropic did same with fable release too where some users were being routed to fable 5.1 so it’s very likely opus 5 is getting routed to 5.2 in claude code can you guys tests and lemme know if it's getting routed for you or not?
0:56
notjazii's profile picture

opus 5 is getting routed to opus 5.2 tested opus 5 on xhigh with the same prompt in devin and claude code but results came out really different > claude code one is clean and more detailed > while devin one is almost there but not the same opus 5 in cc used to be lazy and hard to communicate with, but something changed in the last 2 days now it works for longer and is way easier to communicate with anthropic did same with fable release too where some users were being routed to fable 5.1 so it’s very likely opus 5 is getting routed to 5.2 in claude code can you guys tests and lemme know if it's getting routed for you or not?

J A Z I I

140,113 görüntüleme • 1 ay önce

muse wonder vs swe 2 tested both models with the same prompt at highest reasoning available but came out really different > muse took 24 mins and cost about $18 > swe took 15 mins and cost zero dollars really surprised by how good swe 2 did here but i don't know what muse wonder was doing model is scored above astra and fable 5.1 but it’s performing way worse than both in tests
0:30
notjazii's profile picture

muse wonder vs swe 2 tested both models with the same prompt at highest reasoning available but came out really different > muse took 24 mins and cost about $18 > swe took 15 mins and cost zero dollars really surprised by how good swe 2 did here but i don't know what muse wonder was doing model is scored above astra and fable 5.1 but it’s performing way worse than both in tests

J A Z I I

68,687 görüntüleme • 25 gün önce

Opus 5.2 has to be AGI it just coded an entire 5 minute movie about titanic and showed how everything happened this isn’t even normal coding anymore 😭 anthropic better release this model asap, we can’t wait anymore full video:
2:24
notjazii's profile picture

Opus 5.2 has to be AGI it just coded an entire 5 minute movie about titanic and showed how everything happened this isn’t even normal coding anymore 😭 anthropic better release this model asap, we can’t wait anymore full video:

J A Z I I

112,420 görüntüleme • 1 ay önce

DeepSeek v4.1 flash-1017 drawing Frieren SVG asked modelto make me svg of frieren with reference and give me final output with bg music > took 1 hour 15 mins > used 65.7M tokens > cost $0.70 and here's the output it made, you guys decide if it cooked or nah
0:28
notjazii's profile picture

DeepSeek v4.1 flash-1017 drawing Frieren SVG asked modelto make me svg of frieren with reference and give me final output with bg music > took 1 hour 15 mins > used 65.7M tokens > cost $0.70 and here's the output it made, you guys decide if it cooked or nah

J A Z I I

47,035 görüntüleme • 20 gün önce

sonnet 5.5 just mogged astra tested both models with same prompt at high reasoning and man results are surprising i don't know what anthropic is feeding their models but this is just crazy how a sonnet model is able to give better output then astra? they better release model asap now, can't wait anymore
1:19
notjazii's profile picture

sonnet 5.5 just mogged astra tested both models with same prompt at high reasoning and man results are surprising i don't know what anthropic is feeding their models but this is just crazy how a sonnet model is able to give better output then astra? they better release model asap now, can't wait anymore

J A Z I I

79,926 görüntüleme • 1 ay önce

opus 5.5 is a beast model it just made the best minecraft clone i’ve seen yet, even astra couldn’t make anything like this it has water physics, realistic mechanics and pretty much everything but it’s super slow, even slower than astra play here:
1:23
notjazii's profile picture

opus 5.5 is a beast model it just made the best minecraft clone i’ve seen yet, even astra couldn’t make anything like this it has water physics, realistic mechanics and pretty much everything but it’s super slow, even slower than astra play here:

J A Z I I

76,705 görüntüleme • 1 ay önce

fable 5.5: detailed minecraft one-shot don’t think any other model could one-shot minecraft with this much detail in an hour or two play here:
1:31
notjazii's profile picture

fable 5.5: detailed minecraft one-shot don’t think any other model could one-shot minecraft with this much detail in an hour or two play here:

J A Z I I

11,873 görüntüleme • 5 gün önce

blender test of gpt 6.1 terra model made this hatchet in blender in less than 5 mins and cost was about $1 i don't know what they fed this model but it's the fastest model and i'm using it on max not even fast mode
0:32
notjazii's profile picture

blender test of gpt 6.1 terra model made this hatchet in blender in less than 5 mins and cost was about $1 i don't know what they fed this model but it's the fastest model and i'm using it on max not even fast mode

J A Z I I

20,881 görüntüleme • 11 gün önce

it's day 17 of tibo 28-day challenge and so far today openai has announced two updates first is partnership with google. openai models and codex are coming to google cloud, big news if you're google user second is chatgpt ads, team is expanding ads to 26 more countries, so more users will now see ads while chatting with gpt but don't worry ads will only show on free and go plans. plus, pro and enterprise stay ad-free so do these count as today big improvement or are we getting reset?
0:23
notjazii's profile picture

it's day 17 of tibo 28-day challenge and so far today openai has announced two updates first is partnership with google. openai models and codex are coming to google cloud, big news if you're google user second is chatgpt ads, team is expanding ads to 26 more countries, so more users will now see ads while chatting with gpt but don't worry ads will only show on free and go plans. plus, pro and enterprise stay ad-free so do these count as today big improvement or are we getting reset?

J A Z I I

25,196 görüntüleme • 16 gün önce

fable 5.2 > gpt 6 astra tested both models with same prompt at high reasoning and results came out really different fable next model entered stealth testing today, so i don’t think it's coming out anytime soon from early testing: > huge step up from current fable > output looks better than astra > slower and expensive still running more tests and will drop the outputs soon
0:41
notjazii's profile picture

fable 5.2 > gpt 6 astra tested both models with same prompt at high reasoning and results came out really different fable next model entered stealth testing today, so i don’t think it's coming out anytime soon from early testing: > huge step up from current fable > output looks better than astra > slower and expensive still running more tests and will drop the outputs soon

J A Z I I

62,958 görüntüleme • 1 ay önce

anthropic is testing haiku 5.5 too been using fable 5.5 for the last few days but noticed something weird some outputs from fable 5.1 that knows tibo the reset guy were way worse than sonnet 5.5 but why would it give worse outputs? so i can only think of one thing that team is routing some prompts to haiku 5.5 through fable 5.1 too and testing it that way which makes me think we might see haiku 5.5 in next week or two here's one weird output i got just look at how different these outputs are even tho both were run on fable 5.1 xhigh that knows tibo the reset guy
0:31
notjazii's profile picture

anthropic is testing haiku 5.5 too been using fable 5.5 for the last few days but noticed something weird some outputs from fable 5.1 that knows tibo the reset guy were way worse than sonnet 5.5 but why would it give worse outputs? so i can only think of one thing that team is routing some prompts to haiku 5.5 through fable 5.1 too and testing it that way which makes me think we might see haiku 5.5 in next week or two here's one weird output i got just look at how different these outputs are even tho both were run on fable 5.1 xhigh that knows tibo the reset guy

J A Z I I

43,102 görüntüleme • 1 ay önce

Opus 5.5 vs GPT 6 astra tested both with the same prompt at their highest reasoning settings, using the same devin harness: > opus took 2 hours 10 mins and cost $75 > astra took 1 hour 25 mins and cost $61 opus 5.5 attention to details is on point, it took time to make everything perfect as i wanted but still super slow and ended up costing way more then astra which one did better here?
1:12
notjazii's profile picture

Opus 5.5 vs GPT 6 astra tested both with the same prompt at their highest reasoning settings, using the same devin harness: > opus took 2 hours 10 mins and cost $75 > astra took 1 hour 25 mins and cost $61 opus 5.5 attention to details is on point, it took time to make everything perfect as i wanted but still super slow and ended up costing way more then astra which one did better here?

J A Z I I

55,525 görüntüleme • 1 ay önce