Why? If one gives it a charitable thought I feel like it's obvious she means Claude doesn't do well with convincing sex scenes (I'm guessing as much of that content as possible was removed from the training data and otherwise suppressed). Grok is where the really steamy stuff is at; no filters.
Are there reviews though? Many readers are always ready to publish reviews of stuff they read, so it's mostly just a matter of finding reviews of works by this author.
If it's cheap enough people likely won't bother to return them, but if it's rubbish then there will inevitably be reviews that'll lead to people avoiding the author like the plague. That's the real signal of whether or not something is good.
That link doesn't say anything about Cherny saying software production being solved. It says he said coding is mostly solved. As in it's increasingly easier to generate working code. But coding is neither the beginning nor the end of software production; there is quite a bit more to the thing, from requirements gathering and scoping to thoroughly testing a release to ensure it meets said requirements from the users' perspective.
A few common elements but interestingly also pretty different from my usual flow. Unless I'm fixing issues, I start out by dumping as much as I can think of about what I want built in a brainstorm, then start with that as context for a grill. Depending on how detailed I am and the scope covered, I've been hit by anywhere from say 20 to 80 questions, and when something gets settled it has Gherkin scenarios. Then a spec is created from all that, followed by feature slices with the scenarios as acceptance criteria. Get all those implemented, run standards and spec code reviews over them and it's then up to me to test. I don't review the code, but I have a pretty solid rubric, and I'm always iterating on tools alongside to enforce more and more parts of the flow.
I tend to keep a long-running chat per project for a lead agent, with which all the grilling and ticketing happens, and it then delegates slices to other agents for implementation+review and ensures everything is merged properly after. Maintains context across multiple compacts, and when I do want a fresh session (usually because compact summary had also gotten oversized), I still do a handoff doc so I'm almost never starting from zero in a session, per se.
Idk where people get that from. Having word processors with auto-correct, dictionary and all the other plugins accessible to everyone never solved the writing problem. Why would Claude Code solve software production?
I "accidentally" invented my own tracking system that lives in an org file because I've been using org-mode for project write-ups for years. It was only natural to provide tools for agents to access it all when the AI-centric workflow became a thing.
I liberated myself from the terminal/desktop and am now doing my stuff primarily via phone, so I can freely move around and handle stuff whatever I am. Feeling pretty fried right now because I started with 1 project, and over the session of that project 3 more got dragged in because dependency or tool issue, and they all have multiple features with multiple scenarios that I'm trying to review and unblock, ideally before auto-compact (I have a setup that kicks in after 40m of no activity) because then I have to instruct the agent to mine the previous session(s) for context and it still sometimes misses stuff and... I'm currently failing. I just let them compact now and take a break, and hope too much isn't missed when I get back at them. Definitely need to improve workflow here because it's a heck of a grind. Liberated, but not really.
I have never seen that happen before. What I see is a mention that the classifier stopped it from doing X and it then asks for explicit permission or gives me the command to run myself.
You should note that auto-mode is handled by a different session (and likely model) from your actual. There's no road block or deviation or context flooding; all it does is monitor the model actually doing the work and block it from potentially problematic actions (which you can usually override by saying you explicitly give permission for X), nothing more.
If a given action requires a secret, and you'd like that action to be repeated in the future, how do you expect it to work without said secret included in the save (and without being entangled in secrets management tools)?
Nothing stops someone from committing secrets to public repos, with or without AI. Unless guardrails are put in place that scans repos before push, and only people already wary of secrets leaking would setup said guardrails in the first place.
Devs have been leaking secrets in public repos a long time before now. Nothing new here, except there are now more with dev power, which statistically means more leakage.
According to Claude docs, settings.local.json isn't to be committed. This is just people being the usual sloppy with secrets in repos, not something particular to Claude or AI in general.
Speech can do it all but eventually fatigue sets in if you do try to do it all with speech. Like RSI from too much typing but much faster. Best to use speech for the occasional long prose and steering, and something else for the yes/no/accept/decline options so the throat gets reasonable breaks.
There was always going to be an economic "crisis", just a matter of time. I see it more as a forced positive economic adjustment (bleak for those enamored with the current system).
The quest for a good voice command tool for developers (and others) has been on for many years. Dragon and Talon are 2 that immediately come to mind, mainly for the "others".
This reminds me I have to see what's up with my install. Tried running earlier and got a message that it's secure store is busted, and have options to switch profile or continue and lose data, and all profiles are similarly broken. Luckily I don't keep much in it beyond sites like GMail and anything else not very Firefox friendly. Hoping this doesn't mean I lose access to my Google account as it's only logged in there.
Yeah I've never encountered any of that with Opus. It's pretty good at following instructions, and is also careful re anything sensitive or dangerous. Like just a couple days ago a Telegram bot I have it working on made a reply to a message in a chat that it shouldn't have, and I told it to fix the issue and delete the message (I don't have delete permission in the chat). It did the fix and stopped, saying it won't do anything that touches my service account; I had to tell if specifically again to "do the delete" before it did via the bot. Just one of many cases, and the reprompting can sometimes be annoying but I'm also pretty appreciative that there's way less of a chance it'll do something that has me tearing my hair out.
> open sourcing our proprietary DisplayLink technology ... by educating our competitors and other third parties as to how we implement our market-leading proprietary technology
This makes no sense. If they're screaming about their patents then detailed specs of the tech would be publicly available via the patents office for whomever wants to have a look. They can't make an argument about losing competitive advantage because that's what valid patents are supposed to protect. And I think there is some kind of hobbyist-friendly clause in patent law, similar to fair use, that allows non-commercial 3rd party implementation of patents, so ultimately they have no valid argument against this, just deep pockets to bury hobbyists in legal fees for daring to clean-copy "their" tech.
And you either deal with it, or find an alternative. I'm pretty sure Google has no intention of pulling back, partly because they know the vast majority of users accept what they serve. And partly because they know many of the screamers will go quiet when it gets good enough; all they have to do is ignore them, and they have more than enough in their coffers to ignore anyone who isn't the US president.