They've recently added "lobster" which is an extension for deterministic workflows outside of the LLM, at least partially solving that problem. Also fixed a context caching bug that resulted in it using far more Anthropic tokens than it should have.
It's not. The guy behind Moltbot dislikes crypto bros as much as you seem to. He's repeatedly publicly refused to take fees for the coin some unconnected scumbags made to ride the hype wave, and now they're attacking him for that and because he had to change the name. The Discord and Peter's X are swamped by crypto scumbags insulting him and begging him to give his blessing to the coin. Perhaps you should do a bit of research before mouthing off.
i'd say the crypto angle is only one factor. as is usual in the real world, effects are multifactorial.
clawdbot also rode the wave of claude-code being popular (perhaps due to underlying models getting better making agents more useful). a lot of "personal agents" were made in 2024 and early 2025 which seem to be before the underlying models/ecosystems were as mature.
no doubt we're still very early in this wave. i'm sure google and apple will release their offerings. they are the 800lb gorillas in all this.
How do envision we might disarm an adversary with thousands of nuclear missiles, other than by preemptively nuking them and hoping they don't respond in time. Not really a plausible plan.
You probably wouldn't use it for anything serious, but I've Ralphed a couple of personal tools: Mac menu bar apps mostly. It works reasonably well so long as you do the prep upfront and prepare a decent spec and plan. No idea of the code quality because I wouldn't know good swift code from a hole in the head, but the apps work and scratch the itch that motivated them.
Yes, I write everything in Obsidian and use "Paste from Markdown" in Google Docs. It's a habit I picked up years ago when Docs was much less reliable and lost work.
Plus, I want to deliver the completed document, not my edit history. Even on the occasions that I have written directly in Google Docs, I've copied the doc to obliterate the version history.
Doesn't the Claude APIs recently introduced ability to combine extended thinking with structured outputs overcome this issue? You get the unconstrained(ish) generation in the extended thinking blocks and then structured formatting informed by that thinking in the final output.
I'd always assumed that the patients in Sacks' books were lightly fictionalized composites that combined interesting features from multiple cases. The purpose being to illustrate conditions and aspects of human psychology for a general readership. Since they weren't presented as rigorous case studies, I didn't take them to be that. I find what Sacks did much less irksome than more recent psychological and social studies books that pretend to be presenting rigorous scientific fact when they are, in fact, tendentious bullshit.
I apply the same criteria to any scientific assent. What is the actual practical / clinical relevance? And is it properly studied without p-hacking, correlation/causation confusion and without signs of bias. Following these criteria, 95% of studies are useless, and strangely these overlap massively with the ones that fail to replicate.
Yet I get constantly shit on for having too high standards for scientific rigor.
Small use case but I’m using skills for analysing and scoring content then producing charts. LLM does the scoring then calls a Python script bundled in the skill that makes a variety of PNG charts based on metrics passed in via command line arguments. Claude presents the generated files for download. The skill.md file explains how to run the analysis and how to call the script and with what options. That way, you can get very consistent charts because they’re generated programmatically, but you can use the LLM for what it’s good at.
You have to judge it client by client though. Some are amenable to and grateful for a flatly stated analysis and recommendation, even if it goes against their ideas. Some will feel belittled and undermined. You need both sorts to pay their invoices and refer their peers, so you pick your battles.
This has always frustrated me. You wouldn't go to a doctor, hear that you need an appendix removed, and feel "belittled and undermined"!
The 'problem' (it's a problem from my pov) is that clients simply think they know better when it comes to digital/computer/online stuff. They're used to browsing the web, so they think they know what a good website is. They know how to write a letter in MS Word, so they think they can write good web copy. Etc.
> You wouldn't go to a doctor, hear that you need an appendix removed, and feel "belittled and undermined"!
It happens more than you'd think, even in the HN comment section! Go to any thread where the topic is medical or diseases. Plenty of people distrust their doctor and advocate going to the doctor with your own crackpot theory you "researched" on WebMD. There's a huge anti-credential streak, even here. A lot of people see professional service providers of all kinds as "mere gatekeeping implementors of my own ideas" rather than experts in the field.
A lot of it is internal politics. As a consultant, you see the tip of the iceberg. There may be rational reasons for seemingly irrational decisions that you're not privy to. Your contact's boss wants it done some particular way, so your contact insists on doing it that way. Or your contact has recommended doing it some way internally, and they don't want to be made to look a fool by an outside consultant. Etc.
There’s a site that collects stories about experiences like this. It used to be called Clients From Hell, but got absorbed into a bigger site, called Not Always Right[0]. I suspect some of the stories are apocryphal, but it can be entertaining.
> This has always frustrated me. You wouldn't go to a doctor, hear that you need an appendix removed, and feel "belittled and undermined"!
Many people absolutely do. Hell, look at the number of people who refused to take a safe and effective vaccine during a pandemic!
> The 'problem' (it's a problem from my pov) is that clients simply think they know better when it comes to digital/computer/online stuff.
I must also say there is definitely a reasonable point to challenge your doctor. While they're an expert, they're still human. As a software engineer, I expect my non-expert colleagues to challenge me, and I've come up with better ideas as a result.
As a real-life example, I'm currently trying to get treatment for my Morton's neuroma (foot-nerve issue). The orthopaedic consultant wants to do a neurectomy but I want to investigate alternatives before taking the leap. Why? The alternatives, while they may not work, won't make things appreciable worse, whereas a neurectomy has a 3-6 month recovery if it goes well and can't really be undone if it goes wrong.
reply