正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Test-time learning has a catch that scaling alone does not solve: the state a system writes to in order to learn is also the record a user must inspect to audit it. Optimize it only for learning, and auditability usually degrades. Blog: Part I treats the learning state and... show more

Rei

15,720 subscribers

22,864 次观看 • 2 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

The ultimate blackpill is learning that Gavin Newsom and the CA State Park employees would rather see you burn alive than to see a firefighter take a shovel to this plant on Topanga State Park during a wildfire. Not hyperbole.

The ultimate blackpill is learning that Gavin Newsom and the CA State Park employees would rather see you burn alive than to see a firefighter take a shovel to this plant on Topanga State Park during a wildfire. Not hyperbole.

Mann Made Cinema

1,200,015 次观看 • 8 个月前

This is Milo. He has the reflexes of a sloth and the composure of a statue. Learning catch is going to take a minute. 12/10

This is Milo. He has the reflexes of a sloth and the composure of a statue. Learning catch is going to take a minute. 12/10

WeRateDogs

311,043 次观看 • 5 个月前

This is the best AI agent-first notes app I've found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.

This is the best AI agent-first notes app I've found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.

Dan McAteer

17,164 次观看 • 1 个月前

learning how to sing, play guitar & harmonica, as well as learning the body language and stage presence of a huge rock icon all in the span of only 6 months is incredibly impressive and i will get my client this nom even if i have to do it myself

learning how to sing, play guitar & harmonica, as well as learning the body language and stage presence of a huge rock icon all in the span of only 6 months is incredibly impressive and i will get my client this nom even if i have to do it myself

lee ⭐️

215,325 次观看 • 6 个月前

Pitt has a 🔥 Student Section. They are in the same tier as Purdue and K State.

Pitt has a 🔥 Student Section. They are in the same tier as Purdue and K State.

Big Game Boomer

724,152 次观看 • 3 年前

This figure from HIL-SERL is one of the clearest visualisations of how RL learns differently from imitation learning. The difference comes down to this: imitation learning treats each (state, action) pair as independent. A correction at timestep 20 teaches nothing about timestep 19 or 21. RL propagates reward backward through time. One successful insertion updates the value estimate of every state along the trajectory. So RL builds a full map of "which states lead to success"; imitation learning just memorizes individual snapshots. Setup: a robot inserting a RAM stick into a motherboard slot. Each dot is an end-effector position (Y = lateral, Z = height). Starting position is randomized. Left to right = training progressing. Top row (RL): the policy builds a funnel. Broad at the top, narrowing into the target. It systematically fills in the state space, learning which paths lead to success from many different starting positions. Bottom row (imitation learning / HG-DAgger, same human data): sparse, diffuse, no funnel. The policy only learns near states the human demonstrated. Both have access to the same data, including human corrections, but a completely different structure emerges.

This figure from HIL-SERL is one of the clearest visualisations of how RL learns differently from imitation learning. The difference comes down to this: imitation learning treats each (state, action) pair as independent. A correction at timestep 20 teaches nothing about timestep 19 or 21. RL propagates reward backward through time. One successful insertion updates the value estimate of every state along the trajectory. So RL builds a full map of "which states lead to success"; imitation learning just memorizes individual snapshots. Setup: a robot inserting a RAM stick into a motherboard slot. Each dot is an end-effector position (Y = lateral, Z = height). Starting position is randomized. Left to right = training progressing. Top row (RL): the policy builds a funnel. Broad at the top, narrowing into the target. It systematically fills in the state space, learning which paths lead to success from many different starting positions. Bottom row (imitation learning / HG-DAgger, same human data): sparse, diffuse, no funnel. The policy only learns near states the human demonstrated. Both have access to the same data, including human corrections, but a completely different structure emerges.

Dominique Paul

24,433 次观看 • 5 个月前

Corey DeAngelis recommending the Federal Gov require the Classic Learning Test as a sane alternative to the SAT and ACT duopoly

Corey DeAngelis recommending the Federal Gov require the Classic Learning Test as a sane alternative to the SAT and ACT duopoly

Jeremy Wayne Tate

27,669 次观看 • 10 个月前

Payment infrastructure is still fragmented. Open Payments is the open standard designed to change that. Open Payments Learning Month is 30 days of hands-on learning for developers and fintech builders. Learn the API flow, explore the test environment, and explore ideas with the Open Payments team. Free. Self-paced. Starts June 1.

Payment infrastructure is still fragmented. Open Payments is the open standard designed to change that. Open Payments Learning Month is 30 days of hands-on learning for developers and fintech builders. Learn the API flow, explore the test environment, and explore ideas with the Open Payments team. Free. Self-paced. Starts June 1.

Interledger Foundation

525,972 次观看 • 2 个月前

Last year’s National Audit Office report found that 700,000 children were learning in unsuitable school buildings that required major repairs 🚧 It’s unacceptable that across the country, our children are learning in schools with broken boilers, mouldy walls, crumbling concrete, and flooding classrooms 🏚️ This #generalelection, make sure that every school is properly resourced, and each child has the right conditions to learn 📚 Join the campaign now ➡️

Last year’s National Audit Office report found that 700,000 children were learning in unsuitable school buildings that required major repairs 🚧 It’s unacceptable that across the country, our children are learning in schools with broken boilers, mouldy walls, crumbling concrete, and flooding classrooms 🏚️ This #generalelection, make sure that every school is properly resourced, and each child has the right conditions to learn 📚 Join the campaign now ➡️

Stop School Cuts

10,318 次观看 • 2 年前

Code mode is not a one-shot build. If the result does not fully match your product goal, submit a Bubble Up. Bubble Engine will test, evaluate, and iteratively optimize the underlying Coding SOP, moving refinement from the user to the system. State the goal. Build with Bubble Code. Improve with Bubble Up.

Code mode is not a one-shot build. If the result does not fully match your product goal, submit a Bubble Up. Bubble Engine will test, evaluate, and iteratively optimize the underlying Coding SOP, moving refinement from the user to the system. State the goal. Build with Bubble Code. Improve with Bubble Up.

DAPPOS

28,247 次观看 • 19 天前

She's learning communication and diplomacy. She's learning how to manage the media. She's learning what it takes to stay in the industry. She's a quick learner 🧡 She's knows what they want from her. She has thoroughly evolved herself into the needs of directors and producers 💚

She's learning communication and diplomacy. She's learning how to manage the media. She's learning what it takes to stay in the industry. She's a quick learner 🧡 She's knows what they want from her. She has thoroughly evolved herself into the needs of directors and producers 💚

Forbidden Pleasure

12,448 次观看 • 2 年前

Can we make Transformers better and more efficient for robot learning? Excited to introduce Body Transformer (BoT), an architecture that leverages robot embodiment in the attention mechanism, by treating it as a graph of sensors and actuators.

Can we make Transformers better and more efficient for robot learning? Excited to introduce Body Transformer (BoT), an architecture that leverages robot embodiment in the attention mechanism, by treating it as a graph of sensors and actuators.

Carlo Sferrazza

60,679 次观看 • 1 年前

Lagos is learning from Aba development.... An Ibo man mocks Lagos state for not catching up to the Gigantic development and investment in Aba after seeing 4 buildings for the first time in Aba

Lagos is learning from Aba development.... An Ibo man mocks Lagos state for not catching up to the Gigantic development and investment in Aba after seeing 4 buildings for the first time in Aba

Nononsense

43,297 次观看 • 12 天前

For your baby, play and learning are one and the same. And here’s a great example. This little one, shared to IG by aylinkababy, is exploring cause and effect. As she opens and closes her hand, she flicks the heart shaped bead - causing it to spin on its axis. It’s not just a lesson on how the toy itself works, but a lesson in agency. She’s learning how her own actions can make things happen in the world. (It’s also providing a fantastic opportunity to develop her fine motor skills, as she’s required to strike her fingers against the toy in just the right place to achieve her desired spinning result.) Developmentally, children typically begin exploring cause and effect at around 4 months. And cause and effect toys are a great option, beginning around this age. While this video highlights the spinning bead at its center, note that this toy offers several such opportunities. Shaken it will make a rattling sound. And because of its clear plastic tubing, the balls inside will roll in the direction the toy is shifted. All great opportunities for baby to explore the effects of her actions.

For your baby, play and learning are one and the same. And here’s a great example. This little one, shared to IG by aylinkababy, is exploring cause and effect. As she opens and closes her hand, she flicks the heart shaped bead - causing it to spin on its axis. It’s not just a lesson on how the toy itself works, but a lesson in agency. She’s learning how her own actions can make things happen in the world. (It’s also providing a fantastic opportunity to develop her fine motor skills, as she’s required to strike her fingers against the toy in just the right place to achieve her desired spinning result.) Developmentally, children typically begin exploring cause and effect at around 4 months. And cause and effect toys are a great option, beginning around this age. While this video highlights the spinning bead at its center, note that this toy offers several such opportunities. Shaken it will make a rattling sound. And because of its clear plastic tubing, the balls inside will roll in the direction the toy is shifted. All great opportunities for baby to explore the effects of her actions.

Dan Wuori

18,111 次观看 • 1 年前

Also, please note how Korra doesn't even "change" the origins of bending, it simply expands upon them and provides clarification. "Before you had to learn from dragons!" and in the same episode Wan is LEARNING from dragons.

Also, please note how Korra doesn't even "change" the origins of bending, it simply expands upon them and provides clarification. "Before you had to learn from dragons!" and in the same episode Wan is LEARNING from dragons.

🇵🇸The Nerd 🔜 Otakon 🇵🇸

844,277 次观看 • 2 个月前

State Rep. Danielle Gregoire thinks you're too stupid to know what you're voting for. At a recent meeting, a simple question about public records turned into an attack on the audit and the voters who supported it. 72% backed the audit. They understood.

State Rep. Danielle Gregoire thinks you're too stupid to know what you're voting for. At a recent meeting, a simple question about public records turned into an attack on the audit and the voters who supported it. 72% backed the audit. They understood.

Massachusetts Fiscal Alliance

43,583 次观看 • 4 个月前

Man, the native development tooling is so bad. Why does the preview has to reload every time I switch tabs? Am I missing a setting that keeps it open and preserves the state?

Man, the native development tooling is so bad. Why does the preview has to reload every time I switch tabs? Am I missing a setting that keeps it open and preserves the state?

Sebastian Röhl

63,481 次观看 • 1 年前