Whoever does need it, I give you permission to throw out all your old cables, power adapters, and routers. Yes, on the off chance you do decide you need a Palm III dock, Linksys WRT54G, or Sony PSP charger that means you'd have to buy one on Ebay, but you can cross that $10 bridge if it actually happens.

For me it's not the cost that bugs me when I don't have a part, but rather the disruption to my flow. If I can't get a project done all at once I'm much less likely to ever get it done.

If you don't need an ebook gadget right now, Boox is about to release the Boox Picco as a direct competitor to this. It's in between the X3 and X4 in size, but has a front-lit and potentially higher resolution screen.

I have an X4 Pro (219 ppi) and I use 14pt font because letter widths are pretty uneven at 12pt and on a screen this small I wish I could use my preferred tiny font size. Other than that, it's great.

I'll know we've reached AGI when they don't release an API for the model selling access for a few bucks per task. Seems like AGI would be worth more than that.

We know they'll have replaced horses when a car costs 200 horses.

As long as there is more than one substitute, the prices are not set to equal value. (edit: assuming optimal pricing strat.)

If I had true A(G|S)I, I would release patents, not an API.

I’m also not pro and just need an editor for Youtube or work. I think open source editors like Openshot and Kdenlive are generally underrated and easier to use than they used to be but even for just cutting together clips, adding text, and using keyframes it’s hard to beat how nice Resolve is.

The effort required to do most jobs has gone down and so has the output quality. Rather than doing the same quality work with less effort, some people use LLMs to produce minimum-quality work at minimum effort.

LLMs are a cool tool but we’re over-encouraging use in every domain, even tasks they’re not good at. Every tech company in the world seems to be getting rich though how can I possibly say things would be better without it?

> and so has the output quality

Not my experience at all. The quality has gone up dramatically. Because we also use LLMs to make large scale refactorings that cleans up the code and use it to find lots of bugs that would otherwise have exploded in production at some point in time.

I just used Fable to thoroughly review a PR, and it came up with 5 "Findings that block approval".

I went through each one through the code path (a couple were already considered during implementation), and while all 5 were theoretically accurate, 0 of them were actually reachable.

I wrote them back to Claude point by point and got this back: "I checked all five claims against the code. Your list is correct on all five. I downgrade my verdict: none of the five findings blocks approval. Details and one subtlety below."

This is a usual experience with SOTA models for me and others in my team.

Don't get me wrong, I use it daily; sometimes as a crutch, other times as an accelerator, mostly as a validator/peace of mind. I however don't think that neither velocity or quality is meaningfully changed. But I do spend much more time arguing with a machine.

That is interesting. I use Opus 5 as my daily driver, and it pretty much just works.

For example, a few weeks ago I asked it to analyse my code and find duplicated code that could be extracted into reusable libraries. It found several good examples and did the refactoring. I reviewed the result, and it was 100% how I would have coded it myself.

I do almost no manual coding these days. Opus 5 just works for me.

So it is strange for me to read comments like yours saying that it doesn't work. It would be interesting to find out what makes the difference?

Me too, because I hear a lot of experiences like yours as well. It might be opinionated architecture not fitting the training norm, size of legacy repos/projects, language, or whatever else.

For what it's worth I/we do much less manual coding now too, but it almost always takes a handful of re-prompts to reach expectations.

We can do hooks to reduce superfluous comments or do a second specs-adherence pass, or write failing tests first, but other discrepancies aren't uniform enough to enforce in prompts or context.

I'd love to know the difference too. Or whether long term velocity would be higher by vibing through PRs and deal with issues when things explode or refactor down 2M lines of LLM creep after the fact.

This!! the amount of times that has happened to me in PR. A lot of the times its my fault as I haven't given the agent all of the context ( sometimes intentionally to cross check if it would reach to the same conclusion as me without additional info) but as soon as I give it all the context it would then back track on most of the blockers.

It's interesting how different your experience is from mine. I would love to find out why it works so well for me but not for you.

I use Opus 5 every day, and it just works. It is very rare that I need to do any manual editing.

Is that what's happening in _your_ company?

It's early days, but GLM 5.3 Flash is the first local model that feels good enough to me to be a "main" model without debating whether each problem needs to be sent to a stronger model. DS4 Flash is good enough at implementing given a plan, but I wasn't always a fan of what it came up with when asked to plan something.

The good news is it can only get better from here.

I am enjoying the recently trendy Xteink e-readers that can't do anything but read books. An app store and the internet would just make an e-reader feel like a "worse phone" to me.

It can read books quite okay if it’s mostly text. With photos it’s sluggish. I personally like it but there are other better optionsnout there for a little extra $.