@FinanceYF5: Tesla Optimus Gen 3's hand: 22 degrees of freedom, 50 actuators. In comparison, many competitors only have 6-9 degrees of freedom and far fewer actuators. The gap in dexterous hands is still huge.
Summary
Tesla Optimus Gen 3's dexterous hand has 22 degrees of freedom and 50 actuators, far exceeding competitors (usually 6-9 degrees of freedom), demonstrating a significant technological gap.
View Cached Full Text
Cached at: 08/11/26, 03:39 AM
Tesla Optimus Gen 3’s hands: 22 degrees of freedom, 50 actuators.
By comparison, many competitors only have 6–9 degrees of freedom and far fewer actuators.
When it comes to dexterous hands, the gap is still huge. https://t.co/bn4HVxs4F8
Similar Articles
@FinanceYF5: Cost recipe for humanoid robots: Linear actuators ~30%, Rotary actuators ~25%, Dexterous hands ~20%, AI + vision ~15%, Battery + thermal management <10%. Actuators + hands account for ~75% of the total BOM. High-precision hardware is still the biggest cost.
The tweet breaks down the cost structure of humanoid robots: linear actuators ~30%, rotary actuators ~25%, dexterous hands ~20%. Actuators and hands together account for ~75% of the total BOM, with high-precision hardware still being the largest cost component.
@YRSM_Simon: On DGX Spark, ran same-conditions tests of MiniMax H3 vs LTX 2.3 Eros: 3 sets of prompts, 864×480, 5 seconds. (Prompts from Twitter friend seeddance's examples) H3's action narrative, complex instruction following, and character...
The author ran same-conditions tests of MiniMax H3 and LTX 2.3 Eros video generation models on DGX Spark. Results show H3 is stronger in narrative and instruction following and includes audio, while LTX is about 1.76x faster.
@FinanceYF5: Same task to 4 models: Fable 5 sweeps, but costs 6x more than Opus 4.8. Task: 3 HTML5 physics scenes – broken bridge derailment, canyon collision, monster truck. Fable 5: $3.12, A+, no clipping. GPT 5.5: $1.14, closest to Fable. Opus…
Compares the performance and cost of four AI models (Fable 5, GPT 5.5, Opus 4.8, GLM 5.2) on three HTML5 physics scene tasks. Fable 5 delivers the best quality but costs nearly 6x more than Opus; quality and price are not yet both attainable.
@cat88tw: I spent the afternoon hammering away at gpt-6.1-sol/medium and found this model's personality is genuinely different from the previous 5.6-sol and astra — it's become very steerable, flexible and smart, gets things right on the first try, and almost never meddles unnecessarily or over-engineers. It can also engage with humans on...
The poster shares their experience using the gpt-6.1-sol/medium model, noting that it feels very different in personality from the earlier 5.6-sol and astra models. It is now much easier to steer, flexible and intelligent, gets things done right on the first attempt, rarely over-engineers, and can engage in high-level system architecture discussions with humans — and since it's so cheap, they strongly recommend it.
Good example of the gap between Fable and Sol
The article compares the performance of OpenAI GPT-5.6 Soul and Anthropic Claude Fable 5 in physical 3D printed part replication and autonomous magazine production. Soul slightly outperforms in speed and design precision, but both require significant human intervention in complex real-world tasks, exposing the limitations of current AI in real-world manufacturing tasks.