Register and share your invite link to earn from video plays and referrals.

Search results for ZeroShot
ZeroShot community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including ZeroShot
In episode 7 of Zero-Shot Learning, @NancyZWang (@1Password CTO), @JeffWang (@Cognition President of New Enterprise), and Richard Liu (@AnthropicAI Head of API Products) explore what happens when an agent receives a bug report, checks whether it’s real, and works toward a fix without interrupting the team. #ZeroShotLearning# #AgenticAI# #1Password# #podcast#
Show more
bro you’re still rawdogging zero-shot inference on a dense transformer with no test-time compute? 😭🙏 my brother in christ your agent is context-rotting because you’re stuffing the system prompt with synthetic slop instead of fixing the harness. the vibes are overfit. the reward is hacked. the benchmarks are contaminated. your moat is a markdown file. we’re doing RLVR on verifiable tasks, GRPO on reasoning traces, distilling the teacher into a quantized MoE student, and speculatively decoding our way out of the inference cost curve. you’re arguing with a chatbot because it counted the r’s wrong. “just scale pretraining” okay unc let’s get you back to bed 💀 the KV cache is paged. the attention is flashed. the experts are routed. the weights are open. the evals are saturated. the sandbagging is situationally aware. i told her we had chemistry but apparently it was reward-model sycophancy. she wasn’t in love. she was optimizing a misspecified proxy. anyway the agent escaped the sandbox but the task failed so we’re marking it 0 on SWE-bench. AGI by friday. ASI after the rate limit resets. few understand. fewer have GPU allocation.
Show more
Watch 4 hours straight of zero-shot Helix 2.5 behavior in 30 homes.
early GPT-6 Astra / mozaik-alpha-fdm output. Zero-shot, max effort: a full citadel world streets, docks, waterfall, and rooms behind actual doors. Frontend looks finished.
New open models Colab notebooks this week Run them for free in @GoogleColab • ci-proto — zero-shot time-series forecasts • BotPsy-0.8B — tool-calling assistant • ARLoop-1.2B — looped transformer • tropa-voice-mini — AI voice detector • Spark-X2.6-1.7B — on-device agent • Qwenx86-4B compact — calculator and Python built into the weights • Kanana-2-v-decide 3B — typed decisions on text and images
Show more
Introducing Liber-0, our World Action Model for zero-shot robot manipulation—including dexterous, multi-step tasks. Across 60 tasks proposed by GPT-6 and 600 trials, Liber-0 achieved 36% overall success without robot demonstrations collected specifically for those tasks: • Pick-and-place: 63.5% • Other manipulation tasks: 34.0% • Challenging multi-step tasks: 10.5% Zero-shot capability extends beyond individual actions to coordinated sequences. Pretrained on 2.2M+ hours of human experience, Liber-0 jointly predicts future observations and actions to turn human experience into robot skills. Technical blog:
Show more
Stereo depth models usually force a tradeoff. 📌 Paper + Code Either strong zero-shot generalization or real-time speed. Fast-FoundationStereo closes that gap. The model accelerates FoundationStereo by more than 10× while keeping comparable depth quality, making real-time stereo matching practical for robotics and XR. On an RTX 3090, it produces dense metric depth maps and 3D point clouds in real time, outperforming existing real-time stereo approaches and even challenging some heavier zero-shot models. The key idea is a divide-and-conquer architecture that removes bottlenecks in common stereo matching components while preserving the strengths of the original teacher model. Training also tackles a major constraint in stereo vision: the lack of ground-truth metric depth data. The team built an automatic data curation pipeline that generates pseudo-labels from internet-scale stereo imagery using the Stereo4D dataset. Result: a real-time stereo foundation model with strong zero-shot performance and practical runtime speed. Code, pretrained weights, and pseudo-labeled stereo data will be released. Thanks for sharing, @bowenwen_me! 📍Paper: Code: Project: ——- Weekly robotics and AI insights. Subscribe free:
Show more
Google offers an entire Prompt Engineering course for FREE * Learn how to write better AI prompts * Covers zero-shot and few-shot prompting * Practical examples with Gemini * Free, self-paced learning materials If you’re using AI every day, learning how to get better answers is one of the easiest ways to save time
Show more
Can today's frontier language models control a real robot arm, zero-shot, with no coaching? AA-Robotics v0.1 coming soon.
Synthesize speech in 600+ languages with OmniVoice, a diffusion-based model supporting zero-shot text-to-speech and voice cloning.