robbomacrae
Joined 11 years ago
Karma
998
Submissions
361
Member since
Sep 1
Recent submissions
Comment · 17 days ago
It's a great for tokenmaxxing /s
Comment · 17 days ago
The answer to that is no. A lot of these are released on vibes and showing that it does what it says it does. For most organizations that care about processes and procedures thats... enough? I've worked on agentic development in enterprise and they just want their way to stamp their old methods on to the new agentic world so it can pass through their release hoops.
I've tried to benchmark them the most common public skills including those for ADLC (ie SuperPowers) couple of times here https://orcabot.com/benchmarks/agent-skills. Annoyingly I haven't been able to release one in a while because its been next to impossible to stop the new frontier models from cheating one way or another.
Comment · 24 days ago
Thank you! Love that you did the server art!
I'm absolutely open to PR's. I tried to make it easy to add your own scenes. It's also MIT so feel free to take it and run with it..
1. Yep that makes sense. I haven't really tuned the phase progression much and it def needs a lot of work. For the rocket themes for now they are progressive only until they end but id like to give them the possibility of a bumpy ride so to speak.
2. Yep definitely. Going back to the original server idea.. I'd say it would be even necessary to be able to have a config to make one session have a specific (or random) scene.
3. Yes! I was just thinking about color palettes. ie company or flag colors.
4. https://github.com/samuelclay/crabigator https://drinkcrabigator.com to save others looking it up like I did. Looks great go for it!
I've got some different features in progression so feel free to throw these up as PR's. Otherwise I might get to the config or color palette one day.
Thanks!
Comment · 24 days ago
Thats awesome. I did something similar (much smaller scale) for Claude Code/Pi to show how much it's working https://github.com/robdmac/flow
But this ASCII Art reminds me of my original desire to have something for each server I SSH into to help me keep a mental map of where I am. I'm not SSH'ing into servers anymore but if I was, I'd totally be trying to remake these scenes on the terminal!
Comment · 1 month ago
Ships are ~5x more efficient than trains so unlikely a good trade off. It would have to be a maglev to beat shipping.
Comment · 2 months ago
Yep. OrcaBot has all these features. Free on desktop.
It's been out for 6 months.
Comment · 2 months ago
Most of the open weight models are can be used on device: https://orcabot.com/benchmarks/open-weight-tts
Comment · 2 months ago
Open weight models are getting really good. Specko appears to be focussing on paid services which has its role to play but I have a benchmark in development for Open Weight models here if that is helpful: https://orcabot.com/benchmarks/open-weight-tts.
Still shoring up the details but you can try a sample of all the options and see how they compare in terms of model size, peak RSS, real time factor etc.
Comment · 2 months ago
Then why (and I'm not saying I like the guy) did JD Vance come out so publicly against it? I mean you could certainly argue that was all theater and the UK was indeed doing the US's bidding but at some point you have to apply Occam's razor. The end result is Apple don't offer Advanced Data Protection (encryption) to UK users iCloud backups so its not like that "feature" has worked out.
Comment · 2 months ago
We were demanding the ability to spy on the citizens of our closest allies.
Comment · 2 months ago
I’m not a single issue voter but the sheer incompetence of this particular decision is just too damning. It rightly caused friction with our 5 eyes partners. I would expect readers of hackernews to appreciate how dumb and impossible the request was.
Comment · 2 months ago
“Kier Starmer seemed to actually be doing OK” as someone who voted for his Labour I was immediately regretting it when they tried to force Apple to open a backdoor and they are still trying!
https://www.eff.org/deeplinks/2025/10/uk-still-trying-backdo...
Comment · 2 months ago
Benchmarking public agent skills: Oh My ClaudeCode, Superpowers, Git Ship Done, (previously Get Shit Done), and the Karpathy ones against Swebench-Pro and SlopCodeBench. I have a July vs June breakdown. It's been an interesting learning exercise and reveals the cost/performance impact of using these.
https://orcabot.com https://summer.ai https://talkito.com
contact: rob at ^ the first one
meet.hn/city/uk-London
Socials: - linkedin.com/in/romacrae
Interests: AI/ML, Entrepreneurship, Hacking, Gaming, Music, Programming, Research, Robotics, Sports, Technology, AR/VR
---