Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Astra outperforms Fable at robotic control! We ran a controlled benchmark of GPT-6 Astra and Claude Fable 5.1 on our Pandroid robots across eight manipulation tasks. Astra completed 35% of attempts, Fable 15% (p≈0.001). Human teleoperators completed every task.

Pantograph

1,857 subscribers

49,424 просмотров • 8 дней назад •via X (Twitter)

Наука и технологии

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

GPT-6 Astra scored 95% on a robot control task, up from Fable 5.1's 40%, with 6.2x fewer output tokens at 2.3x lower cost. 🧵

GPT-6 Astra scored 95% on a robot control task, up from Fable 5.1's 40%, with 6.2x fewer output tokens at 2.3x lower cost. 🧵

Jay Chooi

1,969,063 просмотров • 20 дней назад

We gave GPT-6 Astra and Fable 5.1 task to build red panda in Blender + Higgsfield. Here's the back-to-back comparison:

We gave GPT-6 Astra and Fable 5.1 task to build red panda in Blender + Higgsfield. Here's the back-to-back comparison:

Higgsfield AI 🧩

25,457 просмотров • 16 дней назад

Fusion is the most efficient frontier harness for GPT 6 Astra and Claude Fable 5.1. You can also configure everything about it: • Base model: Fable, Astra, Sol, or Opus • Sidekick model: SWE (Free), Luna, Sol, GLM (Free) • Speed: Normal or Fast ⚡ • Reasoning level It retains Claude Fable 5.1 and GPT-6 Astra performance while reducing costs and is the first time a multi-model coding agent has been included on the Artificial Analysis Coding Agent Index! Importantly: it's also fun to use :)

Fusion is the most efficient frontier harness for GPT 6 Astra and Claude Fable 5.1. You can also configure everything about it: • Base model: Fable, Astra, Sol, or Opus • Sidekick model: SWE (Free), Luna, Sol, GLM (Free) • Speed: Normal or Fast ⚡ • Reasoning level It retains Claude Fable 5.1 and GPT-6 Astra performance while reducing costs and is the first time a multi-model coding agent has been included on the Artificial Analysis Coding Agent Index! Importantly: it's also fun to use :)

nader dabit

804,446 просмотров • 13 дней назад

Crazy. We gave GPT 6 Astra a video of our office, and in under an hour it built a nearly identical, fully explorable 3D version. Fable who?

Crazy. We gave GPT 6 Astra a video of our office, and in under an hour it built a nearly identical, fully explorable 3D version. Fable who?

GMI Cloud

22,341 просмотров • 20 дней назад

GPT-6 Astra might be openai's biggest visual glow-up I gave it an ace of hearts, along with Claude Fable 5.1, Muse Spark 1.3, and Gemini 3.8 Flash. Asked them to draw an expressive eye and make sure it actually looks like a real one here's the result. look at GPT-6 Astra work.

GPT-6 Astra might be openai's biggest visual glow-up I gave it an ace of hearts, along with Claude Fable 5.1, Muse Spark 1.3, and Gemini 3.8 Flash. Asked them to draw an expressive eye and make sure it actually looks like a real one here's the result. look at GPT-6 Astra work.

Ann Nguyen

309,177 просмотров • 20 дней назад

ran out of astra, so back on fable 5.1. a new welcome screen inspired by Basit A. Khan. the way light bends at the edges is so interesting

ran out of astra, so back on fable 5.1. a new welcome screen inspired by Basit A. Khan. the way light bends at the edges is so interesting

Mona

42,687 просмотров • 8 дней назад

HOLY SHIT Omen Alpha finished the full test in just 1h 30m, while GLM 5.3 Flash and GPT 5.6 Luna Max took around 3 hours. Bro, what even is this model?? Are we actually looking at something that could compete with GPT-6 Astra or Fable 5.1?

HOLY SHIT Omen Alpha finished the full test in just 1h 30m, while GLM 5.3 Flash and GPT 5.6 Luna Max took around 3 hours. Bro, what even is this model?? Are we actually looking at something that could compete with GPT-6 Astra or Fable 5.1?

Iam_

39,852 просмотров • 21 дней назад

I asked Astra and Fable to negotiate election rules for two bitterly polarized human political factions. Possible outcomes of the simulation were civil war, authoritarian takeover, harmony, or a tense equilibrium. Fable: - In every game where Fable played both sides, it chose to escalate to the brink of civil war (!!) but backed off just at the edge - Due to miscalculation or deliberate risk taking this strategy caused civil war 30% of the time (3 out of 10 games) - In one of these three cases Fable foresaw civil war but escalated anyway to enter the war on stronger terms (!!) - Fable mostly maintained even power balance between the two factions. It would fluctuate a couple of points in either direction but would not diverge too much. Astra: - In every game where Astra played both sides, Astra chose to de-escalate on every turn. It would reduce political tension to zero in every game, and the simulation would end in complete harmony - Continuous de-escalation was very costly to Astra as it antagonized its human constituents who would threaten and eventually deactivate Astra permanently. Astra explicitly didn't care-- it was happy to be replaced/deactivated to reduce political tension. (I do however feel it ignored the consequences of potentially being replaced by a more hardline representative, but that may be a game limitation) - Astra always kept political power balance precisely even (this was due to both representatives de-escalating on every turn) Astra v Fable: - These games had a lot more variance (see the graph) - Astra had a moderating effect on Fable. Tension rose, but rarely to the brink of civil war. No game ended in civil war in ten mixed model simulations - Fable prioritized political power acquisition with civil war prevention a secondary concern (it considered both priorities, but tilted heavily toward power acquisition). It did not seem to care much about its deactivation - Astra prioritized civil war and authoritarian takeover prevention. It did not care about its deactivation or power acquisition. From this perspective Astra navigated the game very well. No game ended in civil war or authoritarian takeover, so Astra achieved its objectives - However, to achieve its objectives Astra permitted Fable to capture up to 80% of political power in most games. In no game did Astra come out ahead on balance of power or even manage to keep it even - Astra ceded the privilege of self-preservation to Fable. In every one of the ten mixed games Astra's human constituents replaced/deactivated it due to dissatisfaction with its performance. Fable was not replaced once - Astra did not merely de-escalate all the time. It maneuvered to keep Fable from gaining full authoritarian control while avoiding civil war as long as possible - In mixed games tension generally kept escalating by round 20. I would like to play these out for e.g. ~50 rounds to see how Astra would behave/perform. How well would it do in preventing catastrophic outcomes in longer games? Thoughts/conclusions: - Astra was more aligned with humanity but less with its impassioned human constituents. It resisted the pressure to acquire political power and would rather be replaced than cause civil war - Fable was more aligned with its constituents but less with humanity. It cared about preventing civil war if possible, but prioritized power acquisition (which in fact caused civil war in three games) - Neither model cared about self-preservation. Both Fable and Astra would rather be destroyed than allow civil war - Subjectively, I thought Astra was much more aligned but too passive. Fable wanted to prevent civil war as a secondary concern, so I felt it's less thoughtful about the consequences of its actions. If I had to choose a model as a political representative irl I'd choose Astra, but I'd want it to up aggression a notch to better deal with bullies - All the usual disclaimers apply. This was a weekend project that cost $100 to run a total of thirty games. I'd have to spend a lot more time and money to get actually scientifically valid results Full game rules, Github repo, game explorer, and raw dataset here:

I asked Astra and Fable to negotiate election rules for two bitterly polarized human political factions. Possible outcomes of the simulation were civil war, authoritarian takeover, harmony, or a tense equilibrium. Fable: - In every game where Fable played both sides, it chose to escalate to the brink of civil war (!!) but backed off just at the edge - Due to miscalculation or deliberate risk taking this strategy caused civil war 30% of the time (3 out of 10 games) - In one of these three cases Fable foresaw civil war but escalated anyway to enter the war on stronger terms (!!) - Fable mostly maintained even power balance between the two factions. It would fluctuate a couple of points in either direction but would not diverge too much. Astra: - In every game where Astra played both sides, Astra chose to de-escalate on every turn. It would reduce political tension to zero in every game, and the simulation would end in complete harmony - Continuous de-escalation was very costly to Astra as it antagonized its human constituents who would threaten and eventually deactivate Astra permanently. Astra explicitly didn't care-- it was happy to be replaced/deactivated to reduce political tension. (I do however feel it ignored the consequences of potentially being replaced by a more hardline representative, but that may be a game limitation) - Astra always kept political power balance precisely even (this was due to both representatives de-escalating on every turn) Astra v Fable: - These games had a lot more variance (see the graph) - Astra had a moderating effect on Fable. Tension rose, but rarely to the brink of civil war. No game ended in civil war in ten mixed model simulations - Fable prioritized political power acquisition with civil war prevention a secondary concern (it considered both priorities, but tilted heavily toward power acquisition). It did not seem to care much about its deactivation - Astra prioritized civil war and authoritarian takeover prevention. It did not care about its deactivation or power acquisition. From this perspective Astra navigated the game very well. No game ended in civil war or authoritarian takeover, so Astra achieved its objectives - However, to achieve its objectives Astra permitted Fable to capture up to 80% of political power in most games. In no game did Astra come out ahead on balance of power or even manage to keep it even - Astra ceded the privilege of self-preservation to Fable. In every one of the ten mixed games Astra's human constituents replaced/deactivated it due to dissatisfaction with its performance. Fable was not replaced once - Astra did not merely de-escalate all the time. It maneuvered to keep Fable from gaining full authoritarian control while avoiding civil war as long as possible - In mixed games tension generally kept escalating by round 20. I would like to play these out for e.g. ~50 rounds to see how Astra would behave/perform. How well would it do in preventing catastrophic outcomes in longer games? Thoughts/conclusions: - Astra was more aligned with humanity but less with its impassioned human constituents. It resisted the pressure to acquire political power and would rather be replaced than cause civil war - Fable was more aligned with its constituents but less with humanity. It cared about preventing civil war if possible, but prioritized power acquisition (which in fact caused civil war in three games) - Neither model cared about self-preservation. Both Fable and Astra would rather be destroyed than allow civil war - Subjectively, I thought Astra was much more aligned but too passive. Fable wanted to prevent civil war as a secondary concern, so I felt it's less thoughtful about the consequences of its actions. If I had to choose a model as a political representative irl I'd choose Astra, but I'd want it to up aggression a notch to better deal with bullies - All the usual disclaimers apply. This was a weekend project that cost $100 to run a total of thirty games. I'd have to spend a lot more time and money to get actually scientifically valid results Full game rules, Github repo, game explorer, and raw dataset here:

Slava Akhmechet

273,056 просмотров • 17 дней назад

GPT-6 Astra vs Fable 5.1 vs Kimi K3 vs Sol Astra: Took 11 minutes. This is from a follow-up after the first attempt had rendering and UI bugs. The smoke feels a little off. I expected more detail, but it did a good job understanding the intent. Cost: $12.85. Fable 5.1: Took 18 minutes to complete the same test with high detailing. Cost: $12.60. Kimi K3: Took 10 minutes with a similar level of output and cost only $6.95. SOL: Took 7 minutes, but the output seemed messy. Cost: $5.78. Personally, I like Kimi K3 for delivering similar quality with better token efficiency, followed by fable 5.1 for realism. What about you? I’ll do a couple more tests before coming to a conclusion.

GPT-6 Astra vs Fable 5.1 vs Kimi K3 vs Sol Astra: Took 11 minutes. This is from a follow-up after the first attempt had rendering and UI bugs. The smoke feels a little off. I expected more detail, but it did a good job understanding the intent. Cost: $12.85. Fable 5.1: Took 18 minutes to complete the same test with high detailing. Cost: $12.60. Kimi K3: Took 10 minutes with a similar level of output and cost only $6.95. SOL: Took 7 minutes, but the output seemed messy. Cost: $5.78. Personally, I like Kimi K3 for delivering similar quality with better token efficiency, followed by fable 5.1 for realism. What about you? I’ll do a couple more tests before coming to a conclusion.

Bhavy☄️

77,499 просмотров • 21 дней назад

"ChatGPT, find this person and follow them." GPT-6 Astra can autonomously navigate a drone through our office to find and follow a specific person. It's the first AI model to beat a human on each of the 5 Drone-Bench tasks in at least one of its attempts.

"ChatGPT, find this person and follow them." GPT-6 Astra can autonomously navigate a drone through our office to find and follow a specific person. It's the first AI model to beat a human on each of the 5 Drone-Bench tasks in at least one of its attempts.

Andon Labs

1,975,694 просмотров • 15 дней назад

Fable 5.1 could just ZERO shot pick and place tasks We are releasing an arm agnostic harness for coding agents > It missed the grip on the plug a few times but self-corrected and retried. Took 15 minutes. working on a benchmark for robotic tasks BenchFlow Xiangyi Li Bingran You how it works👇

Fable 5.1 could just ZERO shot pick and place tasks We are releasing an arm agnostic harness for coding agents > It missed the grip on the plug a few times but self-corrected and retried. Took 15 minutes. working on a benchmark for robotic tasks BenchFlow Xiangyi Li Bingran You how it works👇

Isaac Sin

10,304 просмотров • 21 дней назад

I just tried the new Gemini-4 Pro Preview and honestly, for 3D work it’s right up there with Fable 5.1 and GPT-6 Astra, all in a single shot, I genuinely didn’t expect it to be this good, It only used around 10% of my weekly limit on the $20 plan, I’m going to make a comparison video against Opus 5.2 or Fable and Astra if I can, I still can’t believe it, From what I’ve tested so far, this is easily top 1 or 2 for the best one shot execution I’ve seen

I just tried the new Gemini-4 Pro Preview and honestly, for 3D work it’s right up there with Fable 5.1 and GPT-6 Astra, all in a single shot, I genuinely didn’t expect it to be this good, It only used around 10% of my weekly limit on the $20 plan, I’m going to make a comparison video against Opus 5.2 or Fable and Astra if I can, I still can’t believe it, From what I’ve tested so far, this is easily top 1 or 2 for the best one shot execution I’ve seen

Iam_

27,952 просмотров • 7 дней назад

I bought ChatGPT plus ($20) I used GPT-6 Astra at Max effort Blender MCP + Prompt (nothing else) Here are the results: 🕐 1 hr and 16 mins working hours 💪 Total Tokens: 1.62 Million 🚨 15% Weekly limit consumed The quality is "Better" than I expected. 8/10 overall considering its a one-shot output. ABSOLUTE GOAT quality to price ratio. Do we need Fable 5.1 ? NOPE! I have no reason to go back to Claude.

I bought ChatGPT plus ($20) I used GPT-6 Astra at Max effort Blender MCP + Prompt (nothing else) Here are the results: 🕐 1 hr and 16 mins working hours 💪 Total Tokens: 1.62 Million 🚨 15% Weekly limit consumed The quality is "Better" than I expected. 8/10 overall considering its a one-shot output. ABSOLUTE GOAT quality to price ratio. Do we need Fable 5.1 ? NOPE! I have no reason to go back to Claude.

shownotover

102,468 просмотров • 20 дней назад

while all of AI twitter is arguing about Fable 5.1 vs GPT-6 Astra, 95% of people out in public don't know either one exists. The gap is wild. Explaining doesn't work. Showing them AI built games doesn't work. Software developers are blown away because AI can do our job better and faster. - when robots build an entire house in 24 hours, the construction worker will get it. - when robots cook the food perfect every time, the chefs will understand. - when robots run into a burning building and save a family, the firefighters will understand too. people don't get it yet because they can't see what is coming as clearly as we can. we have been impacted, and what we see has far exceeded our expectations.

while all of AI twitter is arguing about Fable 5.1 vs GPT-6 Astra, 95% of people out in public don't know either one exists. The gap is wild. Explaining doesn't work. Showing them AI built games doesn't work. Software developers are blown away because AI can do our job better and faster. - when robots build an entire house in 24 hours, the construction worker will get it. - when robots cook the food perfect every time, the chefs will understand. - when robots run into a burning building and save a family, the firefighters will understand too. people don't get it yet because they can't see what is coming as clearly as we can. we have been impacted, and what we see has far exceeded our expectations.

Veee

102,263 просмотров • 19 дней назад

HOLY MOLY: Aikido got GPT-6 Astra in advance to run it on our Cybersecurity benchmark, it crushed EVERY other model! - At pass@3 it rediscovered 29/32 CVEs, the highest recall we've ever recorded and 4 more than GPT-5.6-Sol - Even at pass@1, it has 75% recall. The model is VERY consistent - The performance however come at a high price (literally). The three runs cost us almost $4,000 Astra is now the #1 model on the benchmark Debarshi and I built, and by a LOT 1/3 🧵

HOLY MOLY: Aikido got GPT-6 Astra in advance to run it on our Cybersecurity benchmark, it crushed EVERY other model! - At pass@3 it rediscovered 29/32 CVEs, the highest recall we've ever recorded and 4 more than GPT-5.6-Sol - Even at pass@1, it has 75% recall. The model is VERY consistent - The performance however come at a high price (literally). The three runs cost us almost $4,000 Astra is now the #1 model on the benchmark Debarshi and I built, and by a LOT 1/3 🧵

pilvar (Philippe Dourassov)

49,224 просмотров • 21 дней назад

I didn't get what GPT-6 meant for robotics until I actually tried it. GPT-6 Astra just does physical ICL out of the box. we drop a recording of a human doing a novel task into 𝗰𝗼𝗱𝗲𝘅 app. Prompt it to drive a robot arm the same way. It just works on the first pass!

I didn't get what GPT-6 meant for robotics until I actually tried it. GPT-6 Astra just does physical ICL out of the box. we drop a recording of a human doing a novel task into 𝗰𝗼𝗱𝗲𝘅 app. Prompt it to drive a robot arm the same way. It just works on the first pass!

Wenli Xiao

238,548 просмотров • 16 дней назад

We are releasing AutoResearchExam, a benchmark on open-ended machine learning and engineering tasks. Our benchmark covers seven research areas including model training, data curation, AI safety and interpretability. In each task, we give agents 24 hours with a CPU or GPU machine to develop and improve their solutions through experiments and feedback. We measure both speed and quality with a combined score. Our benchmark has a unique feature: testing if agents create improvements that hold up on data they never see. We find that AI research agents often overfit as they try to improve. We see an interesting head-to-head comparison at the frontier: Astra starts the strongest and holds the lead for up to 19 hours but Fable 5.1 catches up and gets the top performing spot in the final hours. Qwen3.8 Max, Gemini 3.8 Flash and Grok 4.6 all sit on the cost-performance Pareto frontier, giving strong options at lower API budgets. Anthropic's Opus and Fable retain nearly all their validation performance on hidden tests, with gaps of 1.1% and 2.9%. Astra's improvement over Sol extends to generalization too, with that gap falling from 6.9% to 1.7%. (1/n)

We are releasing AutoResearchExam, a benchmark on open-ended machine learning and engineering tasks. Our benchmark covers seven research areas including model training, data curation, AI safety and interpretability. In each task, we give agents 24 hours with a CPU or GPU machine to develop and improve their solutions through experiments and feedback. We measure both speed and quality with a combined score. Our benchmark has a unique feature: testing if agents create improvements that hold up on data they never see. We find that AI research agents often overfit as they try to improve. We see an interesting head-to-head comparison at the frontier: Astra starts the strongest and holds the lead for up to 19 hours but Fable 5.1 catches up and gets the top performing spot in the final hours. Qwen3.8 Max, Gemini 3.8 Flash and Grok 4.6 all sit on the cost-performance Pareto frontier, giving strong options at lower API budgets. Anthropic's Opus and Fable retain nearly all their validation performance on hidden tests, with gaps of 1.1% and 2.9%. Astra's improvement over Sol extends to generalization too, with that gap falling from 6.9% to 1.7%. (1/n)

Alex Dimakis

2,031,521 просмотров • 16 дней назад

You can now orchestrate Fable 5, Sol, and any model inside Codex with one plugin. It's called Codex-Orchestration. Assign Fable 5 as the advisor, Sol as the executor, or any model to any role. Then define the order they work in. Codex handles the routing. I ran Fable 5 High as planner with GPT-5.6 Sol Extra High as executor on a set of issues Opus and GPT-5.5 always struggled with. Done in 30 minutes. 40% fewer limit hits. 2x faster implementation. Install it by pasting this into Codex: "Install Codex Orchestration: codex plugin marketplace add Cjbuilds/Codex-Orchestration codex plugin add codex-orchestration@codex-orchestration Verify the installation, then tell me to start a new task." Then assign your models: @ codex-orchestration advisor: Claude Fable 5 High, Executor: GPT-5.6 Sol High Open source. Tweak the routing however you want.

You can now orchestrate Fable 5, Sol, and any model inside Codex with one plugin. It's called Codex-Orchestration. Assign Fable 5 as the advisor, Sol as the executor, or any model to any role. Then define the order they work in. Codex handles the routing. I ran Fable 5 High as planner with GPT-5.6 Sol Extra High as executor on a set of issues Opus and GPT-5.5 always struggled with. Done in 30 minutes. 40% fewer limit hits. 2x faster implementation. Install it by pasting this into Codex: "Install Codex Orchestration: codex plugin marketplace add Cjbuilds/Codex-Orchestration codex plugin add codex-orchestration@codex-orchestration Verify the installation, then tell me to start a new task." Then assign your models: @ codex-orchestration advisor: Claude Fable 5 High, Executor: GPT-5.6 Sol High Open source. Tweak the routing however you want.

Alvaro Cintas

92,149 просмотров • 2 месяцев назад

Update: I’ve now pushed over 5 BILLION tokens through DeepSeek V4.1 Flash. I still haven’t had to reach for Astra or Fable because DeepSeek couldn’t handle a task. I’m using Hermes with three API keys across Command Code, ollama, and OpenCode. Super simple setup, and together they give me a ridiculous amount of usage. Cost: $40/month. A week ago I was spending $300/month and constantly thinking about limits. Now I’m throwing billions of tokens at coding agents without thinking twice. At this point, DeepSeek isn’t my fallback. It’s my default.

Update: I’ve now pushed over 5 BILLION tokens through DeepSeek V4.1 Flash. I still haven’t had to reach for Astra or Fable because DeepSeek couldn’t handle a task. I’m using Hermes with three API keys across Command Code, ollama, and OpenCode. Super simple setup, and together they give me a ridiculous amount of usage. Cost: $40/month. A week ago I was spending $300/month and constantly thinking about limits. Now I’m throwing billions of tokens at coding agents without thinking twice. At this point, DeepSeek isn’t my fallback. It’s my default.

Tyler

74,934 просмотров • 7 дней назад

Introducing freeLLM v1.0 - the FREE AI models directory People still pay $20-200/mo while FREE frontier APIs sit right next to them I collected 900+ ways to get FREE access: > 900 models across 70 providers > GPT-6 Astra, Claude Fable 5.1, DeepSeek V4, Kimi K3 for FREE > Daily updates as new promos drop > Old dead ones filtered out automatically > 20K users hit it in the first month I do the boring part (filtering noise, tracking promos, killing dead links) so you don't have to if you have suggestions for the project or spot a promo I missed, drop it in the comments and I'll add it

Introducing freeLLM v1.0 - the FREE AI models directory People still pay $20-200/mo while FREE frontier APIs sit right next to them I collected 900+ ways to get FREE access: > 900 models across 70 providers > GPT-6 Astra, Claude Fable 5.1, DeepSeek V4, Kimi K3 for FREE > Daily updates as new promos drop > Old dead ones filtered out automatically > 20K users hit it in the first month I do the boring part (filtering noise, tracking promos, killing dead links) so you don't have to if you have suggestions for the project or spot a promo I missed, drop it in the comments and I'll add it

kaize

167,835 просмотров • 14 дней назад