Frankly it seems to be that codex is playing catch-up with claude code and claude code is just continuing to move further ahead. The thing with claude code is it will work longer... if you want it to. It's always had good oversight and (at least for me) it builds trust slowly until you are wishing it would do more at once. When I've used codex (it has been getting better) but back in the day it would just do things and say it's done and you're just sitting there wondering "wtf are you doing?". Claude code is more the opposite where you can watch as closely as you want and often you get to a point where you have enough trust and experience with it that you know what it's going to do and don't want to bother.
That just seems like a UI difference. I've always interrupted claude code added a comment and it's continued without much issue. Otherwise if you just type the message is queued for next. There's no real reason to prefer one over the other except it sounds like codex can't queue messages?
Codex can queue messages, but the queue only gets flushed once the agent is done with whatever it was working on, whereas Claude will read messages and adjust accordingly in the middle of whatever it is doing. It sounds like OP is saying that Codex can now do this latter bit as well.
The problem is if you're using subagents, the only way to interject is often to press escape multiple times which kills all the running subagents. All I wanted to do was add a minor steering guideline.
That is so annoying too because it basically throws away all the work the subagent did.
Another thing that annoys me is the subagents never output durable findings unless you explicitly tell their parent to prompt the subagent to “write their output to a file for later reuse” (or something like that anyway)
I have no idea how but there needs to be ways to backtrack on context while somehow also maintaining the “future context”…
I don't think it will replace SaaS but I do think it can replace the need for a lot of the consultant work that goes around configuring and integrating the SaaS. It will be much easier to have a spec that defines how things need to be configured and the machines can implement it (using the SaaS as tools). Frankly this is the most annoying part. It's not that the B2B stuff can't do whatever, it's that it never gets implemented in ways that aren't a pain in the ass because it's all handled by people who aren't actually using them.
I really don't think it's not going to become "these prompts are specs" and then you have processes of reviewing implementations. It's one thing when you have randos building stuff and they leave etc. Having stored prompts and managed code that uses tools is a different beast.
In my experience this isn’t the case. SaaS systems, at the least the ones that are embracing this sea change seem to recognize that connectivity is key. They are opening APIs and partnering like we’ve never seen. They lack the domain expertise and resources to plumb the last mile. Companies can finally customize and integrate there core SORs at a reasonable price point and if you hire the right people decent technology. It’s a golden era, I do wonder if you’re correct medium/long term but the lack of skill sets to build, deploy, and maintain these solutions is very real. Many can vibe code a great looking app, very few can support it day two even for just a few hundred users.
Bezos didn't buy DC, he bought a newspaper. The commenter was saying that the decline in quality was potentially unrelated to the acquisition and then immediately compared pre and post acquisition quality. That seems like a strange way to make that point and like it might suggest that the acquisition perhaps was related to its decline in quality.
The commenter said they moved back to DC in 2017 and noticed the change then.
Elementary reading skills suggest this means they lived in DC for some significant period of time prior to 2017 as a WP reader, moved away from DC for some unknown period living elsewhere as a non-WP reader, moving back to DC in 2017 when they started reading WP again.
Elementary reading skills would also make it obvious that I'm not talking about their move from and back to DC. Them moving back and forth from DC is certainly irrelevant to WaPo's quality.
They noticed a decline in quality from before and after the acquisition and are using that to conclude that the acquisition didn't impact the quality of the paper. Again, that certainly seems like a strange way to make the point that the purchase didn't impact its quality.
And? Why do you think that matters to what I'm commenting on? Them moving to and from DC is almost certainly completely unrelated to any changes in WaPo's quality.
That there is a personal reason for why their two datapoints are before and after acquisition doesn't change that their two datapoints are before and after acquisition such that it's hard to use those two datapoints to exclude that the ownership had major effects on the quality of the paper's reporting, if anything, it seems extremely suggestive that it did.
That's not what happened though. They were going to endorse a candidate and Bezos interfered and forbade it. There was no "choice" about it at all and that's why I (40+ year subscriber) unsubscribed. Sorry, not sorry.
The key thing is, the endorsement was already written and Bezos intervened to prevent its publication. This was sort of a double-whammy: not just the paper engaging in an act of cowardice, but Bezos finally performing the sort of editorial interference everyone was worried he'd perform when he bought the paper.
Gemini or not, a bot is liable to do some vague arcane something that trips Google autobot whatevers to service-wide ban you with no recourse beyond talking to the digital hand and unless you're popular enough on X or HN and inclined to raise shitstorms, good luck.
Touching anything Google is rightfully terrifying.
Yeah in fact I don't really see what's new in this article except that it hints that it will allow install of software from unverified developers via big scary warnings. Which seems like an improvement from what has been announced previously that only software from verified developers would be allowed.
I already have to configure apps to allow them to install apps on my Pixel... it's like "okay yeah I want to allow F-Droid and Obtainium to install apps" done. Maybe that's not the default or something? Who on earth wants popup ads in Chrome installing shit? And why would anyone want any random app to be able to install additional apps?
reply