Détails

Source

TAO Daily

Publication

26 juin à 19h00

Lien direct

https://taodaily.io/score-enters-the-vision-language-model-race-with-satori-1-0/

Contenu source (brut)

<div id="bsf_rt_marker"></div><div class='booster-block booster-read-block'> <div class="twp-read-time"> <i class="booster-icon twp-clock"></i> <span>Read Time:</span>3 Minute, 41 Second </div> </div> <p class="wp-block-paragraph"><a href="https://taodaily.io/8-takeaways-from-crypto-millies-interview-with-max-sebti-of-score-sn44/">Score (SN44)</a> has spent its first year as a decentralized network where miners compete to build the best computer vision skills across CCTV, dashcams, and drones.</p> <figure class="wp-block-image size-large"><img loading="lazy" decoding="async" width="1024" height="511" src="https://taodaily.io/wp-content/uploads/2026/06/image-196-1024x511.png" alt="" class="wp-image-20868" srcset="https://taodaily.io/wp-content/uploads/2026/06/image-196-1024x511.png 1024w, https://taodaily.io/wp-content/uploads/2026/06/image-196-300x150.png 300w, https://taodaily.io/wp-content/uploads/2026/06/image-196-768x383.png 768w, https://taodaily.io/wp-content/uploads/2026/06/image-196.png 1866w" sizes="(max-width: 1024px) 100vw, 1024px" /><figcaption class="wp-element-caption"><a href="https://www.wearescore.com/">Score’s Vision</a></figcaption></figure> <p class="wp-block-paragraph">That scope just expanded, and the subnet is now training its own Vision Language Model, Satori 1.0 2B, available on <a href="https://taodaily.io/taoweave-just-moved-into-physical-ai-through-manako-labs/">Manako</a>, which folds all nine perception primitives into a single compact model that runs on the camera itself rather than in a data center.</p> <p class="wp-block-paragraph">The skill competition stays live and feeds directly back into making each Satori generation sharper than the last.</p> <div id="ez-toc-container" class="ez-toc-v2_0_76 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction"> <div class="ez-toc-title-container"> <p class="ez-toc-title" style="cursor:inherit">Table of Contents</p> <span class="ez-toc-title-toggle"><a href="#" class="ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle" aria-label="Toggle Table of Content"><span class="ez-toc-js-icon-con"><span class=""><span class="eztoc-hide" style="display:none;">Toggle</span><span class="ez-toc-icon-toggle-span"><svg style="fill: #999;color:#999" xmlns="http://www.w3.org/2000/svg" class="list-377408" width="20px" height="20px" viewBox="0 0 24 24" fill="none"><path d="M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z" fill="currentColor"></path></svg><svg style="fill: #999;color:#999" class="arrow-unsorted-368013" xmlns="http://www.w3.org/2000/svg" width="10px" height="10px" viewBox="0 0 24 24" version="1.2" baseProfile="tiny"><path d="M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z"/></svg></span></span></span></a></span></div> <nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class="ez-toc-link ez-toc-heading-1" href="https://taodaily.io/score-enters-the-vision-language-model-race-with-satori-1-0/#What_a_VLM_Is" >What a VLM Is</a></li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class="ez-toc-link ez-toc-heading-2" href="https://taodaily.io/score-enters-the-vision-language-model-race-with-satori-1-0/#What_Satori_10_2B_Covers" >What Satori 1.0 2B Covers</a></li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class="ez-toc-link ez-toc-heading-3" href="https://taodaily.io/score-enters-the-vision-language-model-race-with-satori-1-0/#The_Family_and_the_Flywheel" >The Family and the Flywheel</a></li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class="ez-toc-link ez-toc-heading-4" href="https://taodaily.io/score-enters-the-vision-language-model-race-with-satori-1-0/#The_Altitude_Just_Changed" >The Altitude Just Changed</a></li></ul></nav></div> <h2 class="wp-block-heading"><span class="ez-toc-section" id="What_a_VLM_Is"></span>What a VLM Is<span class="ez-toc-section-end"></span></h2> <p class="wp-block-paragraph">The simplest way to understand Satori is to start with what a Vision Language Model is and how it differs from a Large Language Model.</p> <figure class="wp-block-image size-large"><img loading="lazy" decoding="async" width="1024" height="502" src="https://taodaily.io/wp-content/uploads/2026/06/image-195-1024x502.png" alt="" class="wp-image-20867" srcset="https://taodaily.io/wp-content/uploads/2026/06/image-195-1024x502.png 1024w, https://taodaily.io/wp-content/uploads/2026/06/image-195-300x147.png 300w, https://taodaily.io/wp-content/uploads/2026/06/image-195-768x377.png 768w, https://taodaily.io/wp-content/uploads/2026/06/image-195.png 1276w" sizes="(max-width: 1024px) 100vw, 1024px" /><figcaption class="wp-element-caption"><a href="https://www.couchbase.com/blog/vision-language-models/" class="broken_link">Couchbase: Review of Language Model</a></figcaption></figure> <p class="wp-block-paragraph">1. <strong>An LLM has read but never seen.</strong> It reasons fluently across text but cannot interpret an image on its own.</p> <p class="wp-block-paragraph">2. <strong>A VLM gives that brain eyes.</strong> It takes pixels and words together, so you can point it at any scene and ask in plain language what is there and what is happening.</p> <p class="wp-block-paragraph">A VLM is not a vision skill stitched to a chatbot. It is one model that understands the full picture natively.</p> <h2 class="wp-block-heading"><span class="ez-toc-section" id="What_Satori_10_2B_Covers"></span>What Satori 1.0 2B Covers<span class="ez-toc-section-end"></span></h2> <figure class="wp-block-image size-large"><img loading="lazy" decoding="async" width="1024" height="584" src="https://taodaily.io/wp-content/uploads/2026/06/image-197-1024x584.png" alt="" class="wp-image-20869" srcset="https://taodaily.io/wp-content/uploads/2026/06/image-197-1024x584.png 1024w, https://taodaily.io/wp-content/uploads/2026/06/image-197-300x171.png 300w, https://taodaily.io/wp-content/uploads/2026/06/image-197-768x438.png 768w, https://taodaily.io/wp-content/uploads/2026/06/image-197.png 2048w" sizes="(max-width: 1024px) 100vw, 1024px" /><figcaption class="wp-element-caption"><a href="https://x.com/MaxScore/status/2069506482341552619/photo/1">Satori’s Dashboard</a></figcaption></figure> <p class="wp-block-paragraph">Satori is built through distillation, which compresses what the best frontier models know into one compact checkpoint. The result runs nine perception primitives in a single forward pass with no teacher needed at inference time.</p> <figure class="wp-block-table"><table class="has-fixed-layout"><tbody><tr><td><strong>Primitive</strong></td><td><strong>What It Does</strong></td></tr><tr><td>Detection</td><td>Identifying objects in a frame</td></tr><tr><td>Open-vocabulary detect-by-name</td><td>Finding objects by free-form description</td></tr><tr><td>Segmentation</td><td>Pixel-level masks for objects</td></tr><tr><td>Description</td><td>Generating natural-language descriptions of scenes</td></tr><tr><td>Reasoning</td><td>Answering questions about what is happening</td></tr><tr><td>OCR (Optical Character Recognition)</td><td>Reading text inside images</td></tr><tr><td>Counting</td><td>Quantifying instances of objects</td></tr><tr><td>Action</td><td>Recognizing what subjects are doing</td></tr><tr><td>Temporal video</td><td>Understanding sequence and change across frames (still emerging)</td></tr></tbody></table></figure> <p class="wp-block-paragraph">Coverage is the point. Strong vision specialists top one or two benchmarks but cover only four or five jobs total. Even GPT-4o natively covers two. Satori covers all nine, posts the highest TextVQA score in its peer set at 83, and handles action