Bluetooth page turner is nice but at this point I have zero interest in a Kindle unless I can load KOReader on it. I might buy one of these if they go on a sale and leave it in a drawer until it's jailbroken. I love my PW5 (jailbroken) but I'd buy a Kobo if they had a 7" screen (Clara) since that's easier to get KOReader on.
Super unimpressed. Initial setup was great and easy, I asked it to work through a GH issue, the cloud machine died multiple times while it was working, and when it said it was done I asked for preview links but it doesn’t have support for that. No problem, I run my own tunnel service, use that. Nope, even with “unrestricted” internet access it couldn’t connect to my tunnel service on a non-standard port.
Ok, fine, use my laptop then… it struggled to download a zip file with its changes, told me it would have the dev stack up soon and…. Silence. It didn’t respond all night long, I messaged it this morning and it showed the typing indicator but sent no message. I tried again, no response…. Cool.
Meanwhile Claude handled 6+ issues end to end including preview URLs that I could test the changes before approving the merge.
This isn’t ready. I do think it’s a glimpse of the future, but it’s not ready.
Tried this out, and it might be due to other apps on my computer or something but the audio it records has a echo. When I go to play back a speaker's voice it sounds I can hear what sounds like 2 audio streams, slightly offset. Maybe it's something to do with SoundSource/ARC or my other meeting transcribing app.
One more feature I'd love is the ability to export the text/transcript in markdown automatically. I have another tool (MeetingTranscriber) that does this and I like that so I can put the transcripts in my Obsidian Vault which I already expose to the various agents I use.
> But it makes me wonder: what if what we loved about this job was never only the code?
This exactly. Look, I "love" code but only because of what it allows me to do and there is plenty of code/coding that I don't love. Not to be too hippy-dippy but I'm a builder, I like to build things. Build things for myself, build things for others. The code was _always_ a means to an end.
Sure, it was cool I had this skill that many people didn't have but I also used to have skill in managing the windows machines and things like the registry. When I first switched to macOS I felt lost, I had this "skill" that was no longer needed but after a while I realized that was a good thing, I wasn't wasting my time fiddling with crap that was just getting in the way of _using_ my computer.
Similarly I may mourn the loss of writing code but at the end of the day code was just a way for me to build, if there are better tools to build (LLMs) then I'm all for it.
I too love building things, but by building things I mean the act of actually building it. Thinking of a problem, devising a solution and then executing the steps to solve the problem, if that doesn’t work, debugging and trying another method and so on. I am not and will never be a fan of buying things, where I just ask for something and it gets made which is what you’re a fan of if you’re honest to yourself.
Agreed, and aside from balancers and some train grid blueprints I don't use external blueprints. There are just some things I don't like re-inventing. Sometimes if I do a back-to-back factorio game I'll bring over some blueprints but I learned early that external blueprints are the quickest way to ruin the game for me.
If you run out of sol medium with $100 you're doing something wrong. Astra destroys your usage, I get 1 day of usage with Astra, but 6 sol is almost unlimited and I only use xhigh.
It’s only nearly unlimited if you haven’t just used a banked reset. After a banked reset your weekly usage gets cut by about 80% (not the week you need to wait to get your normal limits back though). ChatGPT has given me a really good reason to cancel.
Can you elaborate? I've been getting great usage out of my $200/mo plan, and thought I'd try a reset (first time) which was expiring just for giggles. Am I going to get only 20% of it effectively?
I overused Astra in order to drain my weekly, figuring I'd have the reset. (not wastefully, I did get more work done)
I can’t say what will happen to you, but yes, that has been my experience. It is better to wait for your normal full limit to return, because if you use a banked reset you get only 1/5th of the tokens but you still have to wait the full week afterwards for it to reset. 20% would be fine if it didn’t also reset the date your normal reset fires.
I continue to yearn for a harness of harnesses but each one I try (or build) takes me uncomfortably far from the work being done.
I don't want to be a prompt shuttle, though I feel that way sometimes. Performing the same dance for each ticket I work on. My issue is that, to bastardize a common joke/phrase, 50% of the things the agent stops for are things it (or another agent) could answer for me, but it's a different 50% task to task.
With HoH's I constantly feel like I'm getting peppered with unimportant questions or being kept out of the loop of things that really need my eyes on it. Threading that needle has been particularly difficult.
> Bugs are elsewhere in the system, too. Sometimes the search bar in System Settings simply refuses to work.
Yep, I've run into this and issues where clicking the search results or normal sidebar items in settings do nothing. Even after killing and restarting Settings.
Golden Gate is better than Tahoe IMHO but only slightly. I hope they circle back to the myriad of bugs/UI issues they introduced.
My rule has been a 1 year delay but that sometimes makes life hard for Xcode/APIs or changes where your iOS and macOS device must both update for certain features. I bit the bullet and upgraded to 26 after about 6 months but updated to 27 within days because it had to be better than 26, and it is, there are just still a lot of issues.
I can believe that (20x is not 4x of the 5x plan) but I’ve been on the $100/mo Codex and the $200/mo Claude plans and I can run the whole week with multiple agents on Claude, mean while I burned through my whole week in 1 day on Sol. Yes, it’s half the price of my Claude plan but even if OpenAi actually gave 4x usage for the next plan up (which they just halved), it would still be less than the usage I get from Claude.
I used a reset and tried Astra and it also burned though my weekly usage in a day, with a _single_ agent.
I might be totally wrong but I wonder how much is due to context window. Codex felt like it was compacting every 5 seconds, that really screws your cache reads.
reply