Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Inkling 2 Small can paint 👩‍🎨!! (Video + Audio made in code) Comparison below between GLM 5.3 Flash, DeepSeek V4.1 Flash and Qwen 3.8 Flash on the same prompts. ⬇️

41,218 Aufrufe • vor 3 Tagen •via X (Twitter)

14 Kommentare

Profilbild von Surya
Suryavor 3 Tagen

Gummy bears: DeepSeek did the stitched-hatching I requested more literally, but only Inkling's feel like real gummies. Tennis ball: DeepSeek has the best fuzz. But only Inkling put it on a court, with a line and a shadow as requested.

Profilbild von Surya
Suryavor 3 Tagen

Citrus bunting: Inkling's slices are v detailed, it drew seeds and even the wall lining. Balloons: I asked for a view from the floor, looking straight up. Nobody fully got it, but Inkling came closest, with ribbons falling toward you.

Profilbild von Surya
Suryavor 3 Tagen

Median per painting: Inkling ≈$0.032 · 174 s DeepSeek $0.015 · 124 s Qwen $0.020 · 407 s GLM $0.026 · 355 s Inkling costs about a cent more. I was fine with this, because the paintings were better for additional cost.

Profilbild von Surya
Suryavor 3 Tagen

Its only shortcoming is speed. DeepSeek was usually faster, and ~1/2 the price. Inkling sometimes followed the the mood for a prompt more closely at the cost of other details (its gummy bears are glossy, not stitched).

Profilbild von Surya
Suryavor 3 Tagen

Overall, it's the first time an American open-weights model has felt competitive with the Chinese open-weights ecosystem to me. A win for open models. Congratulation to the @thinkymachines team! Really impressive work :)

Profilbild von Martin Ziqiao Ma
Martin Ziqiao Mavor 3 Tagen

@fredahshi I promised that thinky models will have good aesthetic taste 😎

Profilbild von Peichao Du
Peichao Duvor 3 Tagen

Don’t know our model can do this, guess we all have skill issue.

Profilbild von Simon Guo
Simon Guovor 3 Tagen

wow i didn't know inkling 2 small can paint like that! thanks so much for running the experiment @kickingkeys!

Profilbild von Surya
Suryavor 3 Tagen

Excited for Inkling 2 👀

Profilbild von Seongsik Kim
Seongsik Kimvor 3 Tagen

Small but tasteful

Profilbild von tom white
tom whitevor 3 Tagen

have you noticed this model getting frustrated or absent minded on drawings that are challenging or repetitive?

Profilbild von Surya
Suryavor 3 Tagen

It's funny you mention this, while it didn't swear it did have some intresting behaviour. When I was making the video I had it try a lot of difficult things and it acted...grumpy. "Grr." "ARGH." "Ugh." "OK final attempt with strict discipline." idk if this counts as absent minded but a little Russian slipped into its thinking mid-sentence a few times. It wrote a hex code like this one time "#4a3категор". My favourite part though was when it would sign off on its own ideas with a "Cute." Endearing honestly.

Profilbild von The SI Maximalist
The SI Maximalistvor 3 Tagen

Painting, with video and audio made in code, yes, give the coding models an art assignment 🩷

Profilbild von EDDY VU
EDDY VUvor 3 Tagen

Super interesting approach, how are you handling edge cases when scaling concurrent workloads?

Ähnliche Videos

glm 5.3 vs qwen 3.8 vs gemini 3.7 vs deepseek v4 flash four models designed and built three structures each on a physics-backed site, with no dimensions anywhere in the brief the setup: our own agent loop on OpenRouter, a construction site as the tool set – footings, walls, arches, roofs, scaffold, a lamp. the site enforces physics and nothing else: unsupported brick falls, a roof needs walls under it, a worker reaches 3.2 m above whatever he stands on, an arch needs centring until the keystone is set, concrete cures before it carries. no budget ceiling – material cost is tallied and reported, never blocked. tasks: 1. house – a plot and a palette, no plan. shape, height and material are the model's call 2. lighthouse – a headland cut by a gully, with a rock stack standing 30 m offshore. the lamp must burn, it must be the highest thing built, and the keeper must be able to walk to it 3. bridge – a river with one islet and banks at different heights. cross it however you want models: Z.ai glm 5.3 flash, Qwen qwen 3.8 flash, Google DeepMind gemini 3.7 flash, DeepSeek v4 flash vision all twelve objects were finished and signed off by the models themselves. tallest lighthouse is qwen's at 38.4 m, planted on the offshore stack with a bridge run out to it – the only model that read the site that way. deepseek signed off its bridge on an empty riverbed: 0 bricks, 107 minutes, $1.16m of material tallied - total cost, three builds #1 glm 5.3 flash – $0.201 #2 gemini 3.7 flash – $0.871 #3 qwen 3.8 flash – $1.058 #4 deepseek v4 flash – $1.567 - wall clock, three builds #1 gemini 3.7 flash – 91m #2 glm 5.3 flash – 228m #3 deepseek v4 flash – 502m #4 qwen 3.8 flash – 912m - total tokens #1 gemini 3.7 flash – 3,567,052 #2 glm 5.3 flash – 4,732,748 #3 qwen 3.8 flash – 13,469,333 #4 deepseek v4 flash – 18,230,076 - defects logged by the site #1 deepseek v4 flash – 59 #2 gemini 3.7 flash – 132 #3 glm 5.3 flash – 221 #4 qwen 3.8 flash – 350 - material tallied across three builds #1 gemini 3.7 flash – $359,884 #2 glm 5.3 flash – $583,358 #3 deepseek v4 flash – $1,327,484 #4 qwen 3.8 flash – $2,188,625 observations: • glm is the cheap one and nothing here is close – $0.201 for three buildings, $0.042 per million tokens, 6x under gemini's rate • what glm spends it on is bulk, not care: 166,228 bricks in one house and 156 defect weight, the worst single object in the set • gemini is the efficiency line – 91 minutes and 3.57m tokens for all three and an eighth of qwen's clock • gemini also builds the smallest of everything. its lighthouse is 22.5 m against qwen's 38.4, its house 6.9 m against 19.3 • qwen is the maximalist: 1.18m bricks, $2.19m of material, tallest on all three tasks, and 912 minutes – 15 hours – to get there conclusion: twelve finished objects for $3.80 all in, and a 7.8x price spread between the cheapest model and the priciest! follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

26,360 Aufrufe • vor 2 Monaten