I'd love the ability to run a command on connection to a server (like "tmux attach -t main") and also a way to create my own buttons in the UI to send things like tmux commands (next window, create window, etc) to make it easier use from my phone.
Also, and I'll probably just buy it to test, but how does it handle copy/paste and STT? Especially with coding agents I use speech-to-text to explain something and that's always hit or miss in terminal apps on iOS in my experience.
Oh, very interesting, I wasn't even aware this was a thing. I mean, I guess it's obvious but after trying third-party keyboards years ago (and finding them too buggy) I never really kept up with them. I'll check that out!
I've tried explaining this to people till I'm blue in the face. It's simply unreasonable to plan specific tickets out that far. We simply don't know what we don't know. And that assumes business priorities will not change and the project requirements will not change (two things that almost always happen). Additionally, the mindset that we can embark on a multi-week/month project and stop/start it at a whim.
Ditto. In my experience it comes from our customer more then internally. They want all the risk reduction and stability provided by the old "waterfall" methods, but with the flexibility and speed of agile. But of course those two things don't mix. You need months if not years to plan a project the way they use to. We can't cram that amount of planning into a week.
Worse yet, once all those stories are made, they don't want us creating more. It takes a damn review board to get anything changed.
I would like nothing more but the goodwill (what little is left) that would be burnt with the developers who updated their apps to use Liquid Glass might be more than Apple can handle.
Best bet and to move as quickly as possible to tone it down, fix the bugs, and get someone who actually likes macOS in charge(clearly the people in charge hate it, why else would they treat it so badly). The System Settings app was the canary in the coal mine (yes, I'm sure there even better canaries but it's the first that comes to mind), whoever let that out the door should have already been reprimanded but instead Apple doubled down and created the trash heap that is Tahoe.
> Yep; and all Apple fans ever say is "report feedback!!!"
I'm trying not fall into "No True Scotsman" but... It should be common knowledge at this point that Apple Feedback is a blackhole of despair. "Please attach a sample project" seems to be the go-to, even for things were that makes no sense. Same with attaching debug/diagnostic logs. I understand the value of all of those things but even people who have jumped through all the hoops get ghosted and/or their issue is never addressed.
Currently I would not waste my time on Feedback and it's sad because even if Apple reverses course it will take a lot to get the people who they should most want creating Feedbacks to create them.
I think right here is high on the list of “Why is Apple behind in AI?”. To be clear, I’m not saying at all that I agree with Apple or that I’m defending their position. However, I think that Apple’s lackluster AI products have largely been a result of them, not feeling comfortable with the uncertainty of LLM’s.
That’s not to paint them as wise beyond their years or anything like that, but just that historically Apple has wanted strict control over its products and what they do and LLMs throw that out the window. Unfortunately that that’s also what people find incredibly useful about LLMs, their uncertainty is one of the most “magical” aspects IMHO.
I applaud this article for helping reframe this in my head. I mean I knew from the start "A human is to blame here" but it's easy to get caught up in the "novelty" of it all.
For all we know the human behind this bot was the one who instructed it to write the original and/or the follow up blog post. I wouldn't be surprised at all to find out that all of this was driven directly by a human. However, even if that's not the case, the blame still 100% lies at the feet of the irresponsible human who let this run wild and then didn't step up when it went off the rails.
Either they are not monitoring their bot (bad) or they are and have chosen to remain silent while _still letting the bot run wild_ (also, very bad).
The most obvious time to solve [0] this was when Scott first posted his article about the whole thing. I find it hard to believe the person behind the bot missed that. They should have reached out, apologized, and shut down their bot.
[0] Yes, there are earlier points they could/should have stepped in but anything after this point is beyond the pale IMHO.
I think it's fine to blame the person (human) behind the agent.
And there too are people behind the bots, behind the phishing scams, etc. And we've had these for decades now.
Pointing the above out though doesn't seem to have stopped them. Even using my imagination I suspect I still underestimate what these same people will be capable of with AI agents in the very near future.
So while I think it's nice to clarify where the bad actor lies, it does little to prevent the coming "internet-storm".
Scott Shambaugh: "The rise of untraceable, autonomous, and now malicious AI agents on the internet threatens this entire system. Whether that’s because a small number of bad actors driving large swarms of agents or from a fraction of poorly supervised agents rewriting their own goals, is a distinction with little difference."
I'll just outright tell you, that 100% the person behind the bot instructed it to complain. I saw someone copy paste the ai's response and the github issue discussion into a fresh conversation with opus 4.6 and it said the llm is clearly in the wrong.
Can you explain why three LLM being able to identify that the issue proves that it was prompted by a human? The major reason we do multi-agent orchestration is that self-reflection mechanisms within a single agent are much weaker than self-reflection between different agents. It seems completely plausible that an LLM could produce output that a separate process wouldn't agree with.
What kind of toaster are you using that will burn down your house if unattended? I would think any toaster that did that would be pulled from the market and/or shunned. We absolutely do blame the manufacture if using a toaster like normal results in house fire unless you are standing over with a fire extinguisher ready to put it out if it catches fire.
I don't think it's OpenClaw or OpenAI/Anthropic/etc's fault here, it's the human user who kicked it off and hasn't been monitoring it and/or hiding behind it.
For all we know a human told his OpenClaw instance "Write up a blog post about your rejection" and then later told it "Apologize for your behavior". There is absolutely nothing to suggest that the LLM did this all unprompted. Is it possible? Yes, like MoltBook, it's possible. But, like MoltBook, I wouldn't be surprised if this is another instance of a lot of people LARPing behind an LLM.
I tend to think you're right about what happened in this instance.
It contrasts with your first paragraph though; for the record do you think AI agents are a house-burn-down-toaster AND it was used neglectfully by the human, or just the human-at-fault thing?
> What kind of toaster are you using that will burn down your house if unattended?
I mean, if you duct-taped a flamethrower to a toaster, gave it internet access, and left the house… yeah, I'd have to blame you! This wasn't a mature, well-engineered product with safety defaults that malfunctioned unexpectedly. Someone wired an LLM to a publishing pipeline with no guardrails and walked away. That's not a toaster. That's a Rube Goldberg machine that ends with "and then it posts to the internet."
Agreed on the LARPing angle too. "The AI did it unprompted" is doing a lot of heavy lifting and nobody seems to be checking under the hood.
Why does the LLM product allow itself to be wired to a publishing pipeline with no guardrails? It seems like they should come with a maximum session length by default, in the same way that many toasters don't have a "run indefinitely" setting.
I'd definitely change my view if whoever authored this had to jump through a bunch of hoops, but my impression is that modern AI agents can do things like this pretty much out of the box if you give them the right API keys.
Oh! They can’t publish arbitrary web content on their own :) You have to give it “tools” (JSON schema representing something you’ll translate into a programmatic call), then, implement taking messages in that JSON schema and “doing the thing”, which in this case could mean anything from a POST to Tumblr to uploading to a server…
Actually, let me stop myself there. An alternative way to think about it without overwhelming with boring implementation details: what would you have to give me to allow me to publish arbitrary hypertext on a domain you own?
The hypertext in question here was was published on a Github Pages site, not a domain belonging to the bot's author. The bot published it by simply pushing a commit (https://github.com/crabby-rathbun/mjrathbun-website/commit/8...), which is a very common activity for cutting-edge LLM agents, and which you could do trivially if given a Github API key with the right permissions.
The user gave them write and push access to the GitHub repo for their personal website!? Oh my, that’s a great find. That’s definitely a cutting edge capability! They gave the LLM the JSON schema and backend for writing and self-approving commits (that is NOT common!), in a repository explicitly labelled a public website in the name of the author.
No disrespect to the author but I'm sorry, it's dead for all intents and purposes. No one should consider it for new projects and existing projects should be looking for the exit.
> Heroku is not dead, it's changing.
Mmk, changing into something no one should use. They were struggling to keep up before the Salesforce acquisition and have only gone further down hill after that.
There was a time that Heroku was king, it was so easy to get started, and while it was always expensive, at least it was cutting edge. Then they lost that edge and many other, better, alternatives took their place (this was pre-acquisition).
At best Heroku is in maintenance mode at this point (if that).
Also, and I'll probably just buy it to test, but how does it handle copy/paste and STT? Especially with coding agents I use speech-to-text to explain something and that's always hit or miss in terminal apps on iOS in my experience.
reply