Admit I didn't follow the announcements but isn't that a matter of UI? Doesn't seem something that should be baked in the model but in the tooling around it and the instructions you give them. E.g. I've been playing with with GitHub copilot CLI (that despite the bad fame is absolutely amazing) and the same model completely changes its behavior with the prompt. You can have it answer a question promptly or send it on a multi-hour multi-agent exploration writing detailed specs with a single prompt. Or you can have it stop midway for clarification. It all depends on the instructions. Also this is particularly interesting with GitHub billing model as each prompt counts 1 request no matter how many tokens it burns.
It depends honestly. Both are prone to doing the exact opposite of what you asked. Especially with poor context management.
I’ve had both $200 plans and now just have Max x20 and use the $20 ChatGPT plan for an inferior Codex.
My experience (up until today) has always been that Codex acts like that one Sr Engineer that we all know. They are kind of a dick. And will disappear into a dark hole and emerge with a circle when you asked for a pentagon. Then let you know why edges are bad for you.
And yes, Anthropic is pivoting hard into everything agentic. I bet it’s not too long before Claude Code stops differentiating models. I had Opus blow 750k tokens on a single small task.
If you are on a us ansi keyboard and switch to a iso layout (most European layouts are iso) you have I believe two unreachable keys. And the arrangement of the others is slightly different you will have to adapt your muscle memory anyway.
Altgr-intl is pretty good for when you code and write English most of the time and occasionally need accented letters. If you need to write a lot in your native language it's better to get a local layout keyboard.
Seems to me the most expectations they had with the library was about the compression stuff and it did not include that. So in the end it was mostly rev eng. Also in this specific case you are using the library code as documentation about the hardware, the code itself has little value. I doubt it would configure as license violation.
In my every day experience that's pretty risky. The periphery as you call it is often an area where you lack the expertise to spot and correct AI mistakes.
I am thinking about build systems and shell scripts. I see people everyday going to AI before even looking at the docs and invariably failing with non-existent command line options, or worst options that break things in very subtle ways.
Same people that when you tell them why don't you read the f-ing man page they go to google to look it up instead of opening a terminal.
Same people that push through an unknown problem by trial and error instead of reading the docs first. But now they have this dumb counselor that steers them in the wrong direction most of the time and the whole process is even more error prone.
You're wrong. I have all the expertise but none of the time to generate 100s of lines of boilerplate API calls to get the data together, and no interest in formatting it correctly for consumption, let alone doing so state fully to allow interaction. These are trivial problems to solve that are highly tedious and do not affect whatsoever the business at hand. Perfect drudgery for automation, and just scanning the result is easy to verify the output or code.
> . I have all the expertise but none of the time to generate 100s of lines of boilerplate API calls to get the data together, and no interest in formatting it correctly for consumption,
Previously, PiHole used /etc/dnsmasq.d/ with best practice being to put one's own additional config, or overrides, in separate file(s) in that folder.
PiHole v6 appears to have most of that config built-in, and upgrading to v6 removes all of the previous standard config files, leaving only user-created / user-edited files in /etc/dnsmasq.d/ - and PiHole v6 by default no longer imports anything from this folder (to prevent possible incompatibilities).
But it's just a setting, and toggling it brings back the original functionality of importing config from files in that folder. And for me, my custom dnsmasq config worked just the same as it previously did.
Self-esteem that easily turns into hubris though. I think the real seniority shows when you are able to work on a legacy codebase full of the shittiest code and not have the slightest desire to rewrite it all.
No experience with slack but channels in teams are pretty terrible.
Notifications off by default so people create new channels with you as a member, write extremely important information inside them and you find out weeks later.
Each post is like an announcement so nobody uses them for the everyday trivial stuff you need a channel for. For casual technical discussion, asking for help. Whenever you post in a channel, assuming people enabled notifications and your post will be actually seen, everyone is compelled to answer as the UI screams for attention.
And don't get me started about it hiding part of a post by default so you answer thinking you read everything but you missed an essential part because post was 4 rows and 2 were hidden.
