[HN Gopher] Ace: Realtime Computer Autopilot
___________________________________________________________________
Ace: Realtime Computer Autopilot
Author : huerne
Score : 44 points
Date : 2025-04-02 17:55 UTC (5 hours ago)
(HTM) web link (generalagents.com)
(TXT) w3m dump (generalagents.com)
| sherjilozair wrote:
| I'm the founder and CEO of General Agents. Happy to answer
| questions!
| xfr wrote:
| First, I am extremely impressed by the demo. It looks truly
| groundbreaking.
|
| Could you elaborate on the types of tasks and data sources used
| to train Ace, and how these contribute to its performance on
| desktop automation?
|
| Ace is said to outperform other models on your suite of
| computer use tasks. Can you provide more details on these
| benchmarks and how Ace compares to existing automation tools?
| chews wrote:
| From your site, "Ace works like we do--performing mouse clicks
| and keystrokes based on the screen and prompt--trained with <3
| by our team of software specialists and domain experts on over
| a million tasks."
|
| Is there a way to train or augment training on applications
| you've never seen before? We have a bunch of custom Java
| applications that we use in finance, curious about some
| additional automation.
| sherjilozair wrote:
| Ace is actually uniquely designed to support that. Our
| training staff simply record their screens and mouse+keyboard
| events. We transform that into behavior cloning data to train
| the model. It's quite easy for us to do custom agents for
| enterprise or other lesser-known software and workflows.
| Reach out to us at contact@generalagents.com if you're
| interested.
| gkolli wrote:
| Hi! Looks pretty interesting - few questions/thoughts:
|
| 1. Could you talk a bit more about your behavioral-training? If
| ace-control is trained on behavioral recordings, would it
| choose the most efficient path for the agent to take to
| complete a task? I'm guessing humans choose naturally take
| less-optimal steps.
|
| 2. What causes the huge speed increase? I'm guessing there were
| a lot of optimizations made, especially since this behavioral-
| training seems very different from vision models. I'm guessing
| the model is smaller, so it's interesting that accuracy is
| highest. I'd be interested to see a comparison vs. 4o-mini
|
| 3. Would be neat for it to handle instructions offline/locally
| - like "connect me to wifi" ;)
|
| 4. Would be cool if agent could work in the background so I can
| do something else in the meantime. ;)
| timabdulla wrote:
| How does it perform on e.g. WebVoyager, WebArena, or OSWorld?
| These seem to be the oft-cited benchmarks when comparing
| computer-use agents.
| martin_ wrote:
| Amazing performance! Do you anticipate making the model
| available for commercial use or are you primarily focused on
| releasing agents built upon it?
| the__alchemist wrote:
| This isn't what I was expecting at all based on the title!
| iamleppert wrote:
| The recruitment use-case was hilarious, thanks I needed that.
| dilDDoS wrote:
| That example made me wonder if this was satire...I'm guessing
| not, but pretty funny nonetheless. I bet my boss would love me
| texting him the names of random people from LinkedIn.
| cbiscuit wrote:
| cool!!
| misbah143 wrote:
| This is super fast. Future of computer agents. Bullish on this.
___________________________________________________________________
(page generated 2025-04-02 23:01 UTC)