Hacker News Reader

robbomacraeon The Return of Sail Power: Cargo Ships Are Turning Back to the Wind

Ships are ~5x more efficient than trains so unlikely a good trade off. It would have to be a maglev to beat shipping.

robbomacraeon Launch HN: OneCLI (YC S26) – OSS sandboxed agent harness for teams

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

It's been out for 6 months.

robbomacraeon Launch HN: Speko (YC S26) – OpenRouter for Voice AI

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

robbomacraeon Launch HN: Speko (YC S26) – OpenRouter for Voice AI

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.

robbomacraeon Count Binface receives over a quarter of votes in Clacton by-election

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.

robbomacraeon Count Binface receives over a quarter of votes in Clacton by-election

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

robbomacraeon Count Binface receives over a quarter of votes in Clacton by-election

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.

robbomacraeon Count Binface receives over a quarter of votes in Clacton by-election

“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...

robbomacraeon Ask HN: What are you working on? (August 2026)

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

robbomacraeon Homebench – Benchmark local LLMs for speed, memory, and quality

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

robbomacraeon Benchmarking Opus 5 on SlopCodeBench

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.

robbomacraeon Benchmarking Opus 5 on SlopCodeBench

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.

robbomacraeon Benchmarking Opus 5 on SlopCodeBench

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

robbomacraeon Show HN: Juggler – an open-source GUI coding agent, by the creator of JUCE

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.

robbomacraeon Show HN: Juggler – an open-source GUI coding agent, by the creator of JUCE

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...

robbomacraeon Ask HN: What Are You Working On? (July 2026)

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.

robbomacraeon The SpaceX IPO Will Be the Theft of the Century

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.

robbomacraeon The ways we contain Claude across products

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

robbomacraeon 1-Bit Bonsai Image 4B Image Generation for Local Devices

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.

robbomacraeon Claude for Small Business

I'm trying to do this with orcabot.com

A figma like dashboard for turning ClaudeCode, Gemini Cli, Codex into an OpenClaw but with security measures to break the lethal trifecta while running on a VM.

But it's not quite there in terms of usability. I agree that is the hardest part of the equation. It's something I'm constantly experimenting with and haven't found the solution to it yet. Open to feedback!

robbomacraeon Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

I don't think that is entirely fair.. I don't see them stating anywhere they are measuring coding capabilities... "Using complex games to probe real intelligence."

And this seems very much in line with the methodology in ARC-AGI-3.

The results here, in the OP article and in https://www.designarena.ai all tell a similar story: Kimi K2.6 is up and in the SOTA mix.

robbomacraeon Hear your agent suffer through your code

You could have the actual output of the agent turned into TTS using the model of your choice with TalkiTo… or listen to whatever weird sounds this makes. Seems like this is copying that viral Mac moan app. 2026 is weird.

robbomacraeon Human Accelerated Region 1

You sound like you’ve never been disdainfully stared at by a cat..

Really interesting article though. I’m very hopeful AI can help work out how all these things interact.

robbomacraeon US appeals court declares 158-year-old home distilling ban unconstitutional

"Let's be honest here: there is no benefit to alcohol (for example wine) and is only detrimental." - That is a pretty extreme statement and easily falsifiable.

There are many studies a quick google away that show a much more nuanced take ie [0] and [1]. But the strongest evidence is our most successful societies and civilizations have been intentionally drinking alcohol for ~10000 years [2]. If it was only detrimental then I'm pretty sure it would have worked its way out by now. I acknowledge there are negative issues.

[0]: https://www.webmd.com/diet/ss/slideshow-skinny-cocktails [1]: https://nutritionsource.hsph.harvard.edu/healthy-drinks/drin... [2]: https://en.wikipedia.org/wiki/History_of_alcoholic_beverages

robbomacraeon Slightly safer vibecoding by adopting old hacker habits

OrcaBot does this with the VM but whereas the author mentions the risk of GitHub keys being leaked, OrcaBot uses a key broker to ensure the LLM doesn’t have access to any keys. It even works on the API keys to the LLMs themselves. https://orcabot.com/blog#breaking-the-lethal-trifecta

robbomacraeon Claude Code, Claude Cowork and Codex #5

Genuinely surprised they didn't try to get away with department of peace.

robbomacraeon Ask HN: Share your productive usage of OpenClaw

Thanks for mentioning that. The bot filter has been causing trouble so I def need to go and look at it. Debated disabling it but any basic bot that starts a dashboard is spinning up a VM I pay for! Changing browser might be a workaround?

robbomacraeon Show HN: Context Mode – 315 KB of MCP output becomes 5.4 KB in Claude Code

Really cool. A tangential task that seems to be coming up more and more is masking sensitive data in these calls for security and privacy. Is that something you considered as a feature?

robbomacraeon Ask HN: Share your productive usage of OpenClaw

“so the API use is in addition to the subscription, but it can't be helped.” - I beg to differ. OrcaBot.com is a claws that runs using vanilla Claude Code so you can do all that with your regular subscription. Disclosure: I’m the author. The only reason these other claws can’t offer that is because they front it with their own AI.

robbomacraeon Show HN: enveil – hide your .env secrets from prAIng eyes

Thank you! Great feedback. Again agree with you on all points. Will take it onboard!