Jordan-117's favorites

1.		FLUX.2 [Klein]: Towards Interactive Visual Intelligence (bfl.ai)
		227 points by GaggiX 3 days ago \| 58 comments
2.		Uncrossy (uncrossy.com)
		195 points by dgacmu 8 days ago \| 50 comments
3.		Task-free intelligence testing of LLMs (marble.onl)
		69 points by amarble 11 days ago \| 22 comments
4.		Opus 4.5 is not the normal AI agent experience that I have had thus far (burkeholland.github.io)
		879 points by tbassetto 13 days ago \| 1353 comments
5.		Utopian Scholastic (wol.fm)
		70 points by birdculture 14 days ago \| 21 comments
6.		TurboDiffusion: 100–200× Acceleration for Video Diffusion Models (github.com/thu-ml)
		248 points by meander_water 25 days ago \| 46 comments
7.		Qwen-Image-Layered: transparency and layer aware open diffusion model (huggingface.co)
		130 points by dvrp 32 days ago \| 21 comments
8.		GPT Image 1.5 (openai.com)
		522 points by charlierguo 34 days ago \| 256 comments
9.		Qwen3-Omni-Flash-2025-12-01：a next-generation native multimodal large model (qwen.ai)
		316 points by pretext 41 days ago \| 106 comments
10.		Marble by World Labs: Multimodal world model to create and edit 3D worlds (worldlabs.ai)
		48 points by dmarcos 68 days ago \| 20 comments
11.		Qwen3-Omni: Native Omni AI model for text, image and video (github.com/qwenlm)
		571 points by meetpateltech 3 months ago \| 143 comments
12.		Gemini 2.5 Flash Image (googleblog.com)
		1093 points by meetpateltech 4 months ago \| 475 comments
13.		Wan – Open-source alternative to VEO 3 (github.com/wan-video)
		220 points by modinfo 5 months ago \| 38 comments
14.		Show HN: I built a free alternative to Adobe Acrobat PDF viewer (github.com/embedpdf)
		357 points by bobsingor 5 months ago \| 95 comments
15.		Show HN: OWhisper – Ollama for realtime speech-to-text (hyprnote.com)
		289 points by yujonglee 5 months ago \| 75 comments
16.		FFmpeg 8.0 adds Whisper support (ffmpeg.org)
		1033 points by rilawa 5 months ago \| 325 comments
17.		FLUX.1-Krea and the Rise of Opinionated Models (dbreunig.com)
		88 points by dbreunig 5 months ago \| 34 comments
18.		Qwen-Image: Crafting with native text rendering (qwenlm.github.io)
		544 points by meetpateltech 5 months ago \| 159 comments
19.		My app just won best iOS Japanese learning tool of 2025 award (blog) (skerritt.blog)
		122 points by wahnfrieden 22 days ago \| 27 comments
20.		Backing up Spotify (annas-archive.li)
		1980 points by vitplister 30 days ago \| 701 comments
21.		Bye, Mom (aella.substack.com)
		150 points by reducesuffering 37 days ago \| 31 comments
22.		Show HN: OCR Arena – A playground for OCR models (ocrarena.ai)
		216 points by kbyatnal 60 days ago \| 63 comments
23.		Bruno Simon – 3D Portfolio (bruno-simon.com)
		777 points by razzmataks 42 days ago \| 188 comments
24.		Tunnl.gg (tunnl.gg)
		258 points by klipitkas 47 days ago \| 113 comments
25.		Show HN: I built an interactive HN Simulator (ysimulator.run)
		538 points by johnsillings 56 days ago \| 215 comments
26.		FLUX.2: Frontier Visual Intelligence (bfl.ai)
		372 points by meetpateltech 56 days ago \| 117 comments
27.		Adversarial poetry as a universal single-turn jailbreak mechanism in LLMs (arxiv.org)
		384 points by capgre 61 days ago \| 189 comments
28.		Meta Segment Anything Model 3 (meta.com)
		692 points by lukeinator42 61 days ago \| 134 comments
29.		Human Fovea Detector (shadertoy.com)
		492 points by AbuAssar 68 days ago \| 99 comments
30.		Pose Animator – An open source tool to bring SVG characters to life (2020) (tensorflow.org)
		164 points by jerlendds 77 days ago \| 16 comments
		More