Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Span-02: anytime reasoning for decisions. Reasoning models make you pick an effort level and wait. Span-02 takes a deadline and always returns its best decision so far. It gets better the longer it thinks. With reasoning off, it beats Jev at 1/4 of the price, and runs at... show more

Respan

3,276 subscribers

217,916 views • 14 days ago •via X (Twitter)

News & Politics Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Jev + SERV is actually insane. We already showed you can increase Jev's performance with SERV Reasoning. Now we're taking it further, bringing Jev-powered Decision nodes into Graph Sharding with the upcoming SERV v3. Here's a breakdown of how it works: Jev is a decision-making model. Given a task and a set of options, it predicts which path is more likely. Think of the octopus that predicted World Cup results. Jev does that for your business, except it's not luck. It weighs every option and tells you how sure it is. It does this by assigning probabilities to outcomes. It doesn't generate text on its own, so you can't expect it to create a new outcome for you. But that's also what enables it to be lightning fast and dirt cheap. For example, in customer service you can ask Jev how to triage an incoming query and route it to the correct department. It can only select from the list of departments you provide it. This also means it can't hallucinate a new outcome outside the options it's given, which makes it incredibly interesting for OpenServ. In Graph Sharding, we take a single system prompt and break it down into multiple LLM steps with deterministic input and output shapes. Some of these steps require an LLM to produce new output, while others are simply decision routers that determine the next possible path. Traditionally, LLMs are slow and expensive. Breaking a single prompt into multiple steps increases accuracy and reliability by a ton, but it also introduces latency. Jev takes on those decision nodes, which are the backbone of a business process and therefore SERV graphs, and makes them super consistent and lightning fast, lowering the overall cost and latency of graph execution. SERV Reasoning on its own is a great force multiplier for Jev because, like all other models, it works by interpreting input instructions. The clearer those instructions are, the better the model performs. That's where SERV Reasoning comes into play. Just like amplifying any other model, we also amplify the accuracy and consistency of Jev's responses. And now we're bringing Jev-powered Decision nodes into Graph Sharding with SERV v3.

Jev + SERV is actually insane. We already showed you can increase Jev's performance with SERV Reasoning. Now we're taking it further, bringing Jev-powered Decision nodes into Graph Sharding with the upcoming SERV v3. Here's a breakdown of how it works: Jev is a decision-making model. Given a task and a set of options, it predicts which path is more likely. Think of the octopus that predicted World Cup results. Jev does that for your business, except it's not luck. It weighs every option and tells you how sure it is. It does this by assigning probabilities to outcomes. It doesn't generate text on its own, so you can't expect it to create a new outcome for you. But that's also what enables it to be lightning fast and dirt cheap. For example, in customer service you can ask Jev how to triage an incoming query and route it to the correct department. It can only select from the list of departments you provide it. This also means it can't hallucinate a new outcome outside the options it's given, which makes it incredibly interesting for OpenServ. In Graph Sharding, we take a single system prompt and break it down into multiple LLM steps with deterministic input and output shapes. Some of these steps require an LLM to produce new output, while others are simply decision routers that determine the next possible path. Traditionally, LLMs are slow and expensive. Breaking a single prompt into multiple steps increases accuracy and reliability by a ton, but it also introduces latency. Jev takes on those decision nodes, which are the backbone of a business process and therefore SERV graphs, and makes them super consistent and lightning fast, lowering the overall cost and latency of graph execution. SERV Reasoning on its own is a great force multiplier for Jev because, like all other models, it works by interpreting input instructions. The clearer those instructions are, the better the model performs. That's where SERV Reasoning comes into play. Just like amplifying any other model, we also amplify the accuracy and consistency of Jev's responses. And now we're bringing Jev-powered Decision nodes into Graph Sharding with SERV v3.

Armagan Amcalar

366,601 views • 1 month ago

Opus 5.5 works best on 'low' reasoning effort. I ran some tests as part of a project I'm working on. Opus 5.5 on 'low' reasoning vs. 'max' was at parity on task completion but 12x lower cost! Set 'low' reasoning effort by default and increase it for the hardest problems.

Opus 5.5 works best on 'low' reasoning effort. I ran some tests as part of a project I'm working on. Opus 5.5 on 'low' reasoning vs. 'max' was at parity on task completion but 12x lower cost! Set 'low' reasoning effort by default and increase it for the hardest problems.

Dan McAteer

124,009 views • 1 month ago

GPT-5.1 is now available on Replicate. A smarter, more conversational bump from GPT-5 with configurable reasoning effort. And it can count fingers.

GPT-5.1 is now available on Replicate. A smarter, more conversational bump from GPT-5 with configurable reasoning effort. And it can count fingers.

Replicate

84,064 views • 11 months ago

You can now quickly eval GPT-5 and reasoning efforts across your existing responses. With the built-in grader, compare responses to find the best model and reasoning effort for you. ⚡️👀

You can now quickly eval GPT-5 and reasoning efforts across your existing responses. With the built-in grader, compare responses to find the best model and reasoning effort for you. ⚡️👀

OpenAI Developers

79,960 views • 1 year ago

Crunch just ran its first decentralized peer review, in partnership with the Eric and Wendy Schmidt Center at the Broad Institute (Eric and Wendy Schmidt Center). Until now Crunch collected thousands of pieces of code. Now the platform can also collect the reasoning behind that code, and have other Crunchers score it. In the Obesity ML Challenge, Crunchers' models ranked 4.47 million candidate gene pairs. Peer review scores the top submissions and helps decide which get tested in the lab. Only about 40 will make it. Every proposal is read and scored by 4 other Crunchers. Reviews are blind, and each score comes with the reviewer's written reasoning. 316 peer reviews in.

Crunch just ran its first decentralized peer review, in partnership with the Eric and Wendy Schmidt Center at the Broad Institute (Eric and Wendy Schmidt Center). Until now Crunch collected thousands of pieces of code. Now the platform can also collect the reasoning behind that code, and have other Crunchers score it. In the Obesity ML Challenge, Crunchers' models ranked 4.47 million candidate gene pairs. Peer review scores the top submissions and helps decide which get tested in the lab. Only about 40 will make it. Every proposal is read and scored by 4 other Crunchers. Reviews are blind, and each score comes with the reviewer's written reasoning. 316 peer reviews in.

Crunch (Quant/acc)

12,796 views • 3 months ago

Opus 4.6 lets you set the effort level Not every task needs high reasoning. For simpler tasks you can set it to low or medium. Claude thinks less (or skips it entirely), makes fewer tool calls, and gives more concise answers Lower effort = faster responses with fewer tokens!

Opus 4.6 lets you set the effort level Not every task needs high reasoning. For simpler tasks you can set it to low or medium. Claude thinks less (or skips it entirely), makes fewer tool calls, and gives more concise answers Lower effort = faster responses with fewer tokens!

Lydia Hallie ✨

34,866 views • 8 months ago

Zero-shot video reasoning (chain-of-frames) isn’t just for Veo3 — open-source models can understand and edit too! 🕹️ ChronoEdit brings temporal reasoning to image editing. 🔗

Zero-shot video reasoning (chain-of-frames) isn’t just for Veo3 — open-source models can understand and edit too! 🕹️ ChronoEdit brings temporal reasoning to image editing. 🔗

Xuanchi Ren

22,661 views • 1 year ago

Introducing o1 web crawler 🕸️ It crawls entire websites with OpenAI’s new o1 reasoning model and . Just state an objective and it will navigate + return the requested data in a JSON schema. Check it out:

Introducing o1 web crawler 🕸️ It crawls entire websites with OpenAI’s new o1 reasoning model and . Just state an objective and it will navigate + return the requested data in a JSON schema. Check it out:

Eric Ciarla (hiring)

397,759 views • 2 years ago

Codex users: do this right *now*. Max reasoning effort is off by default. Luna at Max reasoning is ~ Sol Medium / Opus 5 Medium level at 1/6th the cost. Change your life today.

Codex users: do this right now. Max reasoning effort is off by default. Luna at Max reasoning is ~ Sol Medium / Opus 5 Medium level at 1/6th the cost. Change your life today.

Dan McAteer

1,144,841 views • 3 months ago

Muse Spark is now live on Venice. AI at Meta’s open-weight reasoning model for code you’d rather keep to yourself. Point it at your repo, wire it into your agents, and run it fully private. Access privately.

Muse Spark is now live on Venice. AI at Meta’s open-weight reasoning model for code you’d rather keep to yourself. Point it at your repo, wire it into your agents, and run it fully private. Access privately.

Venice

10,385 views • 14 days ago

Our open-weight reasoning models are out, and they're great! Run them on your desktop and try them in the Codex CLI: `codex --oss`

Our open-weight reasoning models are out, and they're great! Run them on your desktop and try them in the Codex CLI: `codex --oss`

Alexander Embiricos

45,567 views • 1 year ago

With updated coding and reasoning capabilities, it’s especially strong at building interactive web apps. What used to take 50+ prompts a year ago with 1.5 Flash (left) now takes <10 with far better quality and much more complex UI (right).

With updated coding and reasoning capabilities, it’s especially strong at building interactive web apps. What used to take 50+ prompts a year ago with 1.5 Flash (left) now takes <10 with far better quality and much more complex UI (right).

Google AI

33,381 views • 1 year ago

NVIDIA Nemotron 3 Nano Omni, a new multimodal reasoning model, is now live on Jetson AI Lab and unifies vision, audio, and language into a single reasoning loop. 🙌 Power your NemoClaws by running this model with Ollama, vLLM and other inference frameworks on NVIDIA Jetson hardware. Try it ➡️

NVIDIA Nemotron 3 Nano Omni, a new multimodal reasoning model, is now live on Jetson AI Lab and unifies vision, audio, and language into a single reasoning loop. 🙌 Power your NemoClaws by running this model with Ollama, vLLM and other inference frameworks on NVIDIA Jetson hardware. Try it ➡️

NVIDIA Robotics

16,031 views • 6 months ago

China is literally on 🔥 Baidu from China has launched ERNIE 4.5 and ERNIE X1 and it’s freaking cheap . Here is everything you need to know. ERNIE 4.5 - Native multimodal and Outperforms GPT 4.5 in multiple benchmarks at just 1% of GPT 4.5 price - OpenAI GPT 4.5 – Input: $75 / 1M tokens, Output: $150 / 1M tokens; - ERNIE 4.5 – Input: $0.55 / 1M tokens, Output: $2.20 / 1M tokens ERNIE X1 - A deep thinking reasoning model with multimodal capabilities on par with DeepSeek R1 at only half the price See it in action and check out the pricing details👇 📹 source : yiyan[.]baidu[.]com 1/6 ERNIE 4.5 is a multimodal which can take Audio files as well.

China is literally on 🔥 Baidu from China has launched ERNIE 4.5 and ERNIE X1 and it’s freaking cheap . Here is everything you need to know. ERNIE 4.5 - Native multimodal and Outperforms GPT 4.5 in multiple benchmarks at just 1% of GPT 4.5 price - OpenAI GPT 4.5 – Input: $75 / 1M tokens, Output: $150 / 1M tokens; - ERNIE 4.5 – Input: $0.55 / 1M tokens, Output: $2.20 / 1M tokens ERNIE X1 - A deep thinking reasoning model with multimodal capabilities on par with DeepSeek R1 at only half the price See it in action and check out the pricing details👇 📹 source : yiyan[.]baidu[.]com 1/6 ERNIE 4.5 is a multimodal which can take Audio files as well.

AshutoshShrivastava

324,324 views • 1 year ago

We’ve added a new prompt improver to the Anthropic Console. Take an existing prompt and Claude will automatically refine it with prompt engineering techniques like chain-of-thought reasoning.

We’ve added a new prompt improver to the Anthropic Console. Take an existing prompt and Claude will automatically refine it with prompt engineering techniques like chain-of-thought reasoning.

Anthropic

319,779 views • 1 year ago

Can “chicken” make a base model reason? 🐔 Yes! Why? With the right first tokens, base models can match RL in reasoning. We trace this to learned training data associations and use a simple data edit to make “chicken” elicit reasoning too. blog:

Can “chicken” make a base model reason? 🐔 Yes! Why? With the right first tokens, base models can match RL in reasoning. We trace this to learned training data associations and use a simple data edit to make “chicken” elicit reasoning too. blog:

Sophie Wang

195,773 views • 23 days ago