Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for ByteDance for the week ending September 4, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Nano Banana 2.1.
Category Cover Image Prompt: A psychedelic screen-print gig poster of a stack of vertical phone screens melting into a spinning vinyl record with hypnotic spiral grooves, tiny dancing silhouettes and music notes blooming from the scroll feed into swirling ribbons under a harvest moon, bold hand-lettered title ByteDance curving across the top in Fillmore-era psychedelic typography, electric magenta acid orange deep teal and cream palette with lime green accents, ornate decorative border with falling autumn leaves, flat ink layers with registration offset and visible paper texture.
This Week in ByteDance News
Summary by Claude Sonnet 5.5 based on this week’s links:
The clearest ByteDance item here is a research paper from its Seed team on HarnessDev, a benchmark that scores a model on the runnable agent harness it builds, not just the tasks it completes. One summary says generated harnesses lag human-engineered ones across six creator LLMs and five benchmarks, though the excerpt cuts off before the details.
The rest is thin and indirect. Dreamina-seedance-2.5, which appears to be ByteDance's video model, sits just behind Alibaba's Wan 3.0 on the Video Edit Arena leaderboard, 4 points back. Bilawal Sidhu also speculated about TikTok's For You algorithm paired with on-the-fly video generation, but that is his thought experiment, not an announced product.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to ByteDance
Banger paper from ByteDance Seed. If you are curious about self-evolving agent harnesses, this one is worth your time. (bookmark it) The proposes method, HarnessDev, stops scoring a model on the tasks it completes and scores it on the harness it builds. The agent starts from
https://x.com/omarsar0/status/2095170896407548190
Can LLMs build and evolve their own agent harness? ByteDance Seed introduces HarnessDev, a benchmark that shifts evaluation from task outputs to the runnable infrastructure itself. Across six creator LLMs and five benchmarks, generated harnesses lag human-engineered ones on code
https://x.com/HuggingPapers/status/2095545764793520204
Exciting news: Wan 3.0 by @Alibaba_Wan has claimed the #1 spot in the Video Edit Arena! With 1414 ps, Wan 3.0 leads dreamina-seedance-2.5 by 4 pts and MiniMax-H3 by 22 pts. This release marks @Alibaba_Wan’s debut in the Video Edit Arena. This newer Arena now features 10 models
https://x.com/arena/status/2093143153167810608
How soon until an AI agent can organically get a million followers on a video platform like youtube or tiktok – and do so fully autonomously in a couple of months?
https://x.com/bilawalsidhu/status/2094081526459716053
Imagine when this type of just-in-time media generation is connected to something as powerful as tiktok’s for you algorithm. The feed could almost read your mind and materialize videos right before you scroll to them. It would be the most addictive form of media ever created.
https://x.com/bilawalsidhu/status/2093856257165668467
Leave a Reply