Hacker News: robbomacrae

New comment by robbomacrae in "Launch HN: OneCLI (YC S26) – OSS sandboxed agent harness for teams"

robbomacrae — Wed, 19 Aug 2026 18:37:36 +0000

Yep. OrcaBot has all these features. Free on desktop.

It's been out for 6 months.

New comment by robbomacrae in "Launch HN: Speko (YC S26) – OpenRouter for Voice AI"

robbomacrae — Mon, 17 Aug 2026 20:16:42 +0000

Most of the open weight models are can be used on device: https://orcabot.com/benchmarks/open-weight-tts

New comment by robbomacrae in "Launch HN: Speko (YC S26) – OpenRouter for Voice AI"

robbomacrae — Mon, 17 Aug 2026 20:15:14 +0000

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.

New comment by robbomacrae in "Count Binface receives over a quarter of votes in Clacton by-election"

robbomacrae — Fri, 14 Aug 2026 21:22:41 +0000

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.

New comment by robbomacrae in "Count Binface receives over a quarter of votes in Clacton by-election"

robbomacrae — Fri, 14 Aug 2026 19:25:01 +0000

We were demanding the ability to spy on the citizens of our closest allies.

New comment by robbomacrae in "Count Binface receives over a quarter of votes in Clacton by-election"

robbomacrae — Fri, 14 Aug 2026 18:45:18 +0000

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.

New comment by robbomacrae in "Count Binface receives over a quarter of votes in Clacton by-election"

robbomacrae — Fri, 14 Aug 2026 18:16:16 +0000

“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...

New comment by robbomacrae in "Ask HN: What are you working on? (August 2026)"

robbomacrae — Sun, 09 Aug 2026 17:46:05 +0000

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/benchmarks

New comment by robbomacrae in "Homebench – Benchmark local LLMs for speed, memory, and quality"

robbomacrae — Tue, 04 Aug 2026 17:41:51 +0000

FYI the GitHub URL is 404ing

I’ve been integrating benchmarks into OrcaBot either locally on the app or online at orcabot.com. Mostly as a way of giving an easy way to verify my own posted benchmarks. There is a template for running SlopCodeBench. Working on a TTS one next.

Wasn’t sure if there would be a lot of interest in this space. It can be costly but some provided such as OpenAI let you hammer their subscription with these.

Source available: https://github.com/Hyper-Int/OrcaBot

New comment by robbomacrae in "Benchmarking Opus 5 on SlopCodeBench"

robbomacrae — Wed, 29 Jul 2026 11:56:28 +0000

Thats right and to go even further I'm judging them on a metric they didn't necessarily target. A client I work with uses skills such as these to apply their own processes on the agentic development lifecycle. But users should also understand the trade-offs. I think it's intuitive that the extra steps and processing invoked by these skills adds to the token cost - this benchmark aims to put numbers on that as well as time and accuracy.

New comment by robbomacrae in "Benchmarking Opus 5 on SlopCodeBench"

robbomacrae — Tue, 28 Jul 2026 20:05:03 +0000

Yep that was interesting but imho not completely unexpected. My original hypothesis was that these agent skills are castles built on sand and that the models would quickly adapt and make them redundant. Also the skills use up context and I think a lot of them partially focus on investigating a large complex codebase properly... which is wasted on greenfield projects.

New comment by robbomacrae in "Benchmarking Opus 5 on SlopCodeBench"

robbomacrae — Tue, 28 Jul 2026 07:34:19 +0000

SCB is definitely an underrated benchmark. For me the unique selling point is that it more closely mirrors software development by not stopping after a single task. The agent has to keep code clean. The only disadvantage is all the problems are greenfield and not git inited so the agents don’t make use of git diffs.

I’ve used SCB as part of my assessment of agent skills (superpowers, GSD etc) https://orcabot.com/labs/do-skills-improve-coding-agent-accu...

There is a small but growing community on discord for discussing SCB so if interested please join https://discord.gg/BrC4BA9sVj

Do Skills Improve Coding Agent Accuracy?

robbomacrae — Wed, 22 Jul 2026 00:12:36 +0000

Article URL: https://orcabot.com/labs/do-skills-improve-coding-agent-accuracy

Comments URL: https://news.ycombinator.com/item?id=49000144

Points: 2

# Comments: 0

Show HN: Free Desktop OrcaBot for macOS

robbomacrae — Wed, 22 Jul 2026 00:06:41 +0000

OrcaBot is a virtualized sandbox for securely orchestrating your AI tools.

Its secrets broker keeps credentials hidden from agents. Network egress controls help prevent data exfiltration. The tools and agents themselves run inside an isolated virtual machine.

Until now, OrcaBot has run exclusively in the cloud using Fly.io virtual machines. Those machines cost money to operate, which is why the cloud version of OrcaBot requires a subscription.

Now OrcaBot Desktop is available for free on macOS

Comments URL: https://news.ycombinator.com/item?id=49000099

Points: 2

# Comments: 0

New comment by robbomacrae in "Show HN: Juggler – an open-source GUI coding agent, by the creator of JUCE"

robbomacrae — Tue, 14 Jul 2026 16:22:37 +0000

I think I'm more on your side on that rather than letting agents go wild like Steve Yegge/Pete Steinberger do. In fact OrcaBot quickly adapted into a knee jerk reaction to OpenClaw because I saw that as inherently dangerous.

But with regard to Juggler and orchestration, have you seen "claude agents" (started in the terminal as claude agents instead of just claude). I ask because your tree like approach has similarities to how claude agents manages claude agents/subagents doing tasks with the ability to drill down in to each at a time which is why for me its not such a leap from what you already have.

New comment by robbomacrae in "Show HN: Juggler – an open-source GUI coding agent, by the creator of JUCE"

robbomacrae — Tue, 14 Jul 2026 16:08:39 +0000

This looks really interesting and a unique take on the AI agent orchestration. I think we need a bunch of experiments in this area as it's clear we are entering a new paradigm and the tools for it are lacking. The session tree in particular has merits.

I've got my own attempt with OrcaBot (short for orchestration of bots). It's also been a 6 month solo build experiment. I'm not trying to plug.. just that I'm also neck deep in Steve Yegge's Stage 8 AI-assisted coding chart and understand how much thought and effort went into this.

Thinking about where this is all going with talking to AI like fully autonomous employees similar to @Claude can you see a comms app type approach that combines something like slack with your tree/thread structure? It's somewhat orthogonal to your "inspect everything" but could intersect by bringing click through/open in options...

New comment by robbomacrae in "Ask HN: What Are You Working On? (July 2026)"

robbomacrae — Sun, 12 Jul 2026 22:23:30 +0000

https://orcabot.com

OrcaBot was my Jan+Feb attempt to defeat the lethal trifecta whilst offering all the bells and whistles of a claw like sandbox: https://orcabot.com/blog#breaking-the-lethal-trifecta

This month I've been working on the free desktop version which is available as of today but probably carries a few too many bugs to not be worth promoting just yet.

New comment by robbomacrae in "The SpaceX IPO Will Be the Theft of the Century"

robbomacrae — Thu, 04 Jun 2026 07:19:44 +0000

AAPL and MSFT have a P/E an order of magnitude lower than TSLA whilst both having revenue growth % yoy in the teens. They both make over a $100b in PROFIT a year. TSLA's? $4b and shrinking btw. Their highest P/E's since 2005 was under 50. AAPL reached 100 in June 2003 (around the time of the iTunes Store release.. mid iPod era but pre iPhone).

Comparing with MSFT and AAPL makes TSLA look even more insane.

New comment by robbomacrae in "The ways we contain Claude across products"

robbomacrae — Thu, 04 Jun 2026 05:41:32 +0000

I've been working on addressing the exfiltration leg as well as the other legs of the lethal trifecta in my OrcaBot [0][1] platform and I thought I had it mostly covered with the help of a network snitch and egress allowlist until I read these comments.

Domain fronting and Steganography in commits to public repos are not solved and probably in all honesty not completely solvable. I wonder if this well end up like in banking where no bank can completely eliminate fraud. I've got some ideas to do bank like fraud detection within OrcaBot now so might be able to limit the impact a little. Thank you!

[0] https://orcabot.com/blog#breaking-the-lethal-trifecta

[1] https://github.com/Hyper-Int/OrcaBot

New comment by robbomacrae in "1-Bit Bonsai Image 4B Image Generation for Local Devices"

robbomacrae — Sun, 31 May 2026 16:11:51 +0000

I believe it's the way the HN algorithm works. In order to give new and obscure posts a shot, it will add them to peoples feeds in their front page and see how they measure. Otherwise new posts wouldn't get seen and the flywheel would never get started.

So everyone acts as a sort of beta tester for obscure posts.