Maybe it's unfair to judge an author's current opinion by their past opinion - but since the piece is ultimately an opinion based on their own experience I'm going to take it along a giant pile of salt that the author's standards for the output of AI tools are vastly different than mine.
Hah, I read that as well and made a big "hmmmmmmmmm" sound...
The last time I talked to someone about OpenClaw and how it is helping them, they told me it tells them what their calendar has for them today or auto-tweets for them (i.e., non-human spam). The first is as simple as checking your calendar, and the second is blatant spam.
Anyone found some good use cases beyond a better interface for AI code assistance?
A dev on my team was trying to get us to setup OpenClaw, harping on about how it would make our lives easier etc, etc. (even though most of the team was against the idea due to the security issues and just not thinking it would be worth it).
Their example use case was for it to read and summarize our Slack alerts channel to let us know if we had any issues by tagging people directly... the Slack channel is populated by our monitoring tools that also page the on-call dev for the week.
The kicker... this guy was the on-call dev that week and had just been ignoring the Slack channel, emails and notifications he was getting!
This should be the opening for every post about the various "innovations" in the space.
Preferably with a subsequent line about the manual process that was worth putting the extra effort into prior to the shiny new thing.
I really can imagine a better UX then opening my calendar in one-click and manual scanning.
Another frequent theme is "tell me the weather." One again, Google home (alexa or whatever) handles it while I'm still in bed and let's me go longer without staring at a screen.
The spam use-case is probably the best use-case I've seen, as in it truly saves time for an equal or better result, but that means being cool with being a spammer.
This is a pretty simple thing to boil the ocean over but it was fun nonetheless.
I've been applying for jobs but I don't want Gmail notifications on my phone because of all the spam, I'm really picky about push notifications. I told my openclaw adjacent ai bot to keep an eye and let me know if any of the companies I applied to send me an email. Worked great. CEO LARPing at its finest.
Also a big fan of giving it access to my entire obsidian vault so if I'm on the go instead of trying to use obsidian on the phone I just tell it what I need to read or update.
I'm not running openclaw itself. I am building a simpler version that I trust and understand a lot more but ostensibly it's just another always on Claude code wrapper.
Not via OpenClaw, but I automate breakdowns of my analytics and I recently started getting digests of social media conversations relevant to my interests. It's also good for monitoring services and doing first line triage on issues.
I think a sizable proportion of people just want to play "large company exec". Their dream is to have an assistant telling them how busy their day is, all the meetings they have, then to go to those meetings and listen to random fluff people tell them while saying "mmh yeah what a wise observation" or "mmh no not enough synergy here, let's pivot and really leave our mark on this market, crunch the numbers again".
I can't come up with any other explanation for why there seems to be so many people claiming that AI is changing their life and workflow, as if they have a whole team of junior engineers at their disposal, and yet have really not that much to show for it.
They're so white collar-pilled that they're in utter bliss experiencing a simulation of the peak white collar experience, being a mid-level manager in meetings all day telling others what to do, with nothing tangible coming out of it.
Everybody here probably already has an opinion about the utility of coding agents, and having it manage your calendar isn't terribly inspired, but there is a lot more you can do.
To be specific, for the past year I've been having numerous long conversations about all the books I've read. I talk about what I liked, didn't like, the ideas and and plots I found compelling or lame, talks about the characters, the writing styles of authors, the contemporary social context the authors might have been addressing, etc. Every aspect of the books I can think off. Then I ask it for recommendations, I tell it given my interests and preferences, suggest new books with literary merit.
ChatGPT just knocks this out of the park, amazing suggestions every time, I've never had so much fun reading than in the past year. It's like having the world's best read and most patient librarian at your personal disposal.
My experience with plain Claude Code is that I can step back and get an overview of what I'm doing, since I tend to hyperfocus on problems, preventing me from having a simultaneous overview.
It does feel like being a project manager (a role I've partially filled before) having your agency in autopilot, which is still more control than having team members do their thing.
So while it may feel very empowering to be the CEO of your own computer, the question is if it has any CEO-like effect on your work.
Taking it back to Claude Code and feeling like a manager, it certainly does have a real effect for me.
I won't dispute that running a bunch of agents in sync won't give you an extension of that effect.
The marketing of OpenClaw is amazing. They had a one-liner install that didn't work, started the hype-train days before they changed the name of the product and have everyone from nerd influencers to CNBC raving about it.
> Anyone found some good use cases beyond a better interface for AI code assistance
Well... no. But I do really like it. It's just an always-on Claude you can chat with in Telegram, that tries to keep context, that has access to a ton of stuff, and it can schedule wakeup times for itself.
> Anyone found some good use cases beyond a better interface for AI code assistance?
Yesterday, I saw a demo of a product similar to OpenClaw. It can organize your files and directories and works really great (until it doesn't, of course). But don't worry, you surely have a backup and need to test the restore function anyway. /s
Edit:
So far, I haven’t found a practical use case for this. To become truly useful, it would need access to certain resources or data that I’m not comfortable sharing with it.
Our cognition evolves over time. That article was written when the Rabbit R1 presentation video was first released, I saw it and immediately reflect my thoughts on my blog. At that time, nobody had the actual product, let alone any idea how it actually worked.
Even so, I still believe the Rabbit has its merits. This does not conflict with my view that OpenClaw is what is truly useful to me.
I think this shows an unfettered optimism for things we don't know anything about. Many see this as a red flag for the quality of opinions.
> R1 is definitely an upgraded replacement for smartphones. It’s versatile and fulfills all everyday requirements, with an interaction style akin to talking to a human.
You seemed pretty certain about how the product worked!
> Today, Rabbit R1 has been released, and I view it as a milestone in the evolution of our digital organ.
You viewed it as a “milestone in the evolution of our digital organ” without you let alone anyone having even tested it?
Yet you say ”That article was written when the Rabbit R1 presentation video was first released, I saw it and immediately reflect my thoughts on my blog.”?
There's a difference between the author being more upfront about it and straight-up lying on multiple locations that zero AI is involved. It's stated on the landing page, documentation and GitHub - and there might be more locations I havent' seen.
Personally, I would want no involvement in a project where the maintainer is this manipulative and I would find it a tragedy if any people contributed to their project.
On a side note, the NATO alphabet is quite normalised in the Netherlands - most telephone operators will default to it when providing you information and likewise there is an expectation on you to use it when providing spelling sensitive information such as emails.
When used in the domain of fashion "good taste" describes someone who has a unique way of selecting clothes that just mesh well together - clothes that by themselves independently are meaningless, no matter their make or quality, but when combined together create a powerful effect - much greater than the sum of their parts.
I was hoping the article would go in that direction - what subjective combination is a software engineer deciding on that you can argue is truly a matter of taste and not just a technical decision about a trade-off.
I would say this this article itself may be an example of bad taste. It meanders across a couple of disparate topics in software engineering, independently each section is competently written but as a whole they really don't sell the "look" the article was aiming for.
(I don't mean to discourage future writing by the author - I think it's a potentially excellent choice of topic. I'm just giving my two cents here on the execution.)
I don't agree with the statement that clothes can be "by themselves independently are meaningless". Garments carry cultural, historical and symbolic weight even before they're combined. And fashion is hardly mainly about combining outfits.
And fashion is a lot about tradeoffs too. Not just in the production, but also in the day to day wearing and mix-and-matching part.
Meaningless in the context of an outfit - not necessarily whether the garment itself may have meaning to someone. You may surely be in possession of a couple of random trinkets of great historic significance but if you just mesh them all together into one outfit you might simply end up with a mess on your hands. A garment may well be the centerpiece of an outfit - but it is ultimately always the combination that is important.
Im sure you've seen examples of this yourself - you can absolutely sport a Ray Ban in good taste and you've almost surely seen someone believe themselves to be fashionable because they are wearing a Ray Ban.
Also, I'm not suggesting fashion as a whole is about combing outfits - merely that being able to combine varying pieces of clothing into a cohesive whole is an expression of good taste.
I think the line of thinking you want to explore has more to do with how we perceive beauty and elegance. That has been the subject of philosophers all over in our recorded history, and I doubt a single article will be able to cover this.
Christopher Alexander studied this deeply for building architecture, and his ideas had influenced many thinkers of software architecture; Alexander asserts that there is a thing to objective beauty. Alexander’s keynote to the OOPSLA conference is worth reading, as is Roy Fielding’s dissertation. The “values” mentioned in this article is organized as “architectural properties” in Fielding’s dissertation.
> what subjective combination is a software engineer deciding on that you can argue is truly a matter of taste and not just a technical decision about a trade-off.
I put down to taste many things that I believe are technical decisions about trade-offs but that I cannot absolutely verify or which I believe the trade off is so very small that it doesn't actually matter.
Funny, I think it was one of the more insightful and well put together articles on a subject that usually elicits very hand-wavy unactionable statements.
You're comparing apples and oranges. Good taste in fashion is much more subjective than in software engineering, obviously because one stays a subjective discipline while the other always ends up in formal science.
What's interesting is that software engineering starts in social science where most choices are made subconsciously or at least not discussed with other people.
Most engineers and technical persons don’t have good fashion taste, so they have a hard time understanding good taste in general.
The great majority of technical things are not cool to normal humans, they’re geeky. Programming languages are not cool.
In programming one has to therefore start from “not cool” and move down the scale:
Uncool: Rust, C++, most languages
Painfully uncool: anything functional and weird. Bash, Linux, etc.
This comment annoyed me so much I had to get an actual keyboard to respond.
First off, the concept of "good taste" is much, much broader than only applying to clothing based fashion. You can have good taste in practically any field that involves any amount of creativity/choice: cooking, painting, writing, music, programming, video game design, etc, the list is practically infinite.
As such, the idea that most "engineers and technical persons" don't "understand good taste" is incredibly silly. It's entirely possible, perhaps even probable that the average programmer lacks good taste in terms of fashion, but that says nothing at all about good taste in other areas.
Secondly, having good taste and being able to apply it is also wildly different. I can recognize what looks good in fashion or paintings without being myself able to achieve that.
Thirdly, there's really no such thing as a "normal human". The longer you live, assuming you're willing to actually examine your experiences, the more you'll learn that the trite expression "everyone is unique" really is accurate.
Just as a semi-random example, it might be tempting to think of watching football (nfl) as "normal". According to a quick google, the average nfl game gets like 17-20million viewers, and even assuming that's accurate/all unique people/etc, it's a very large number in absolute terms but its less than 10% of the population of america.
So if you took a random group of 100 americans, something like 6-7 would have watched a football game last week[1]. Now that's still many times larger than the number of people who wrote code last week, but it's not some kind of overwhelming majority that "everyone" does.
[1] Yes these numbers are extremely imprecise, it's rhetorical
It is broader since it applies to things which can be perceived visually, but does not apply to any random creative activity. The list is finite and programming is not on it.
Furthermore, taste in one area is more likely to manifest in other areas. Somebody that has good taste in fashion would likely have good taste in interior decoration or art.
> Secondly, having good taste and being able to apply it is also wildly different. I can recognize what looks good in fashion or paintings without being myself able to achieve that.
Ok, but applying it is the interesting part.
> Thirdly, there's really no such thing as a "normal human". The longer you live, assuming you're willing to actually examine your experiences, the more you'll learn that the trite expression "everyone is unique" really is accurate.
The things that make individuals truly unique are often irrelevant in the greater scheme. One could draw a line across continents and ages to connect quite similar people.
According to my Iranian friends (even the most hardline Ayatollah haters), most Iranians hate the regime, but they'll rally behind them if boots land on the ground.
Many of them still look at the Iran-Iraq war with a shade of Iranian patriotism (not sure there's a word to capture that actual feeling of sad memories of losing family members, coupled with a patriotic sense of duty).
The younger generation, not so much, since they didn't have to live through that hell.
> The few Iranians I know are against the regime, but I don't know how the wider picture looks.
my experience with Iranians I know are the same. the regime is not partitularly liked by the Iranians but they are no doubt united behind him now because (and for good reason) they likely believe whoever the israelis would appoint as the leader of Iran would be categorically worse.
I find it hard to believe foreign intervention can do anything other than rally support.
A lot of Americans deeply oppose Trump, but how many of them would support a Chinese invasion with the express objective of overthrowing him and installing a new regime? I suspect very few, and instead you'd probably get a backlash of support for Trump.
Maybe it's unfair to judge an author's current opinion by their past opinion - but since the piece is ultimately an opinion based on their own experience I'm going to take it along a giant pile of salt that the author's standards for the output of AI tools are vastly different than mine.
reply