What they are redacting is pretty questionable though. Entire pages being suspiciously redacted with no explanation (which they are supposed to provide). This is just my opinion, but I think it's pretty hard to defend them as making an honest and best effort here. Remember they all lied about and changed their story on the Epstein "files" several times now (by all I mean Bondi, Patel, Bongino, and Trump).
It's really really hard to give them the benefit of the doubt at this point.
My favorite is that sometimes they redact the word "don't". Not only does it totally change the meaning of whatever sentence it's in, the conspiracy theory is that they had a Big Dumb Regex for redacting /Don\W+T/i to remove Trump references
Maybe some day, but as a claude code user it makes enough pretty serious screw ups, even with a very clearly defined plan, that I review everything it produces.
You might be able to get away without the review step for a bit, but eventually (and not long) you will be bitten.
Reviewing what it produces once it thinks it has met the acceptance criteria and the test suite passes is very different from wasting time babysitting every tiny change.
True, and that's usually what I'm doing now, but to be honest I'm also giving all of it's code at least a cursory glance.
Some of the things it occasionally does:
- Ignores conventions (even when emphasized in the CLAUDE.md)
- Decides to just not implement tests if gets spins out on them too much (it tells you, but only as it happens and that scrolls by pretty quick)
- Writes badly performing code (N+1)
- Does more than you asked (in a bad way, changing UIs or adding cruft)
- Makes generally bad assumptions
I'm not trying to be overly negative, but in my experience to date, you still need to babysit it. I'm interested though in the idea of using multiple models to have them perform independent reviews to at least flag spots that could use human intervention / review.
I use that to feed back into my spec development and prompting and CI harnesses, not steering in real time.
Every mistake is a chance to fix the system so that mistake is less likely or impossible.
I rarely fix anything in real time - you review, see issues, fix them in the spec, reset the branch back to zero and try again. Generally, the spec is the part I develop interactively, and then set it loose to go crazy.
This feels, initially, incredibly painful. You're no longer developing software, you're doing therapy for robots. But it delivers enormous compounding gains, and you can use your agent to do significant parts of it for you.
> You're no longer developing software, you're doing therapy for robots.
Or, really, hacking in "learning", building your knowhow-base.
> But it delivers enormous compounding gains, and you can use your agent to do significant parts of it for you.
Strong yes to both, so strong that it's curious Claude Code, Codex, Claude Cowork, etc., don't yet bake in an explicit knowledge evolution agent curating and evolving their markdown knowledge base:
Unlikely to help with benchmarks. Very likely to improve utility ratings (as rated by outcome improvements over time) from teams using the tools together.
For those following along at home:
This is the return of the "expert system", now running on a generalized "expert system machine".
I assumed you'd build such a massive set of rules (that claude often does not obey) that you'd eat up your context very quickly. I've actually removed all plugins / MCPs because they chewed up way too much context.
It's as much about what to remove as what to add. Curation is the key. Skills also give you some levers to get the kind of context-sensitive instruction you need, though I haven't delved too deeply into them. My current total instruction set is around ~2500 tokens at the moment
Linux development has a blueprint they could follow. Like the principle of least privilege. These aren’t cutting edge concepts.
Also I’m not sure the tradeoffs of adding security to an editor are that big of a deal. Are we really seeing revolutionary stuff here? Every now and then I check out VS Code only to realize Vim is still 10x better.
No doubt, but I (and I suspect many others) rarely update plugins and I have a very select list of plugins that I use (mostly from one guy), and I just use git to manage them. I never see churn, but that might just be me.
I assume you could probably do the same with VSCode, but I suspect there's a cultural difference that pushes you to always update? Do things stop working because of churn?
If the person got up and walked away I'm not sure what damage you'd be doing by reasonably removing your car from blocking others while waiting for police.
It can be not known to some, but it's not uncommon for person with serious injures to walk and run in the first monents after accident. Injuries can sometimes be hidden.
So "walk away" cannot be a legal criteria for decision to move the car or not. There can be some very serious consequences for the "but I did not know" in case of the following collapse or any other damage.
I wonder if the workers of the time were as responsible for the propaganda as we are... It seems like the ultimate heist when capital can get labour to propagate their own messaging.
Airplane! also features tons of other TV and movie references doesn’t it? Basically what would have happened in these well known shows and movies when you add absurd scenarios while still playing it straight (the joke is never acknowledged of course!).
Not just jokes and scenarios - it's full of many actors that for years (and decades) played very serious "leading man" type roles. Seeing all these all-american heroes just being utter idiots helped make it so impactful.
> I'm hopeful that some day Linux will have enough users where the media companies can't ignore them. Hopefully, that day is sooner than later.
Does YouTube and Netflix work? That's the lion's share right there. A lot of users probably don't even care about the other streaming platforms. I'm probably being too optimistic, but I think the upcoming Steam machines will have a significant adoption of the linux desktop. Microsoft is certainly working 'round the clock to alienate their users.
If you're using a "common browser" on Linux (Firefox/Chrome) Netflix should work, just at 720p for most of the content. If you're using a minor Chromium based fork the customized Chromium package provided by your distro it probably doesn't have Widevine by default.
The same is true for running a vanilla Chromium build on Windows, the big difference is the quality of content you can get on Windows can be higher than 720p in the mainstream browsers (as long as the rest of the system is compliant as well).
One correction to my message above: apparently Chrome on Windows is still 720p for Netflix, it was Edge that had 4k support. Or you can install the Netflix App on Windows too.
I agree it's a bit silly, but I think a lot of people don't really care about quality so long as they can watch it. I guess that'd also explain how Netflix gets away with such low bitrates for even the "high quality" versions of content.
I don't think I've seen Netflix comment on this since a long time ago, but back in 2018 it was:
- 15% PC
- 10% Smartphone
- 5% Tablets
- 70% TVs
In terms of viewing hours https://www.statista.com/chart/13191/netflix-usage-by-device.... So definitely most viewing on TV, but still something like 1/3 of households with TVs don't have a 4k TV at all (as of 2025) in the first place. Hard to definitively say more since Netflix & others don't seem to publish the numbers often.
I'd love to find out I'm wildly wrong though and have a bunch of people willing to push Netflix to have higher quality content... but so many people don't even seem to pay for the premium plan with 4k (anecdotally, Netflix doesn't seem to publish numbers on that) that I'm not holding my breath as I sit here with UHD Blu-Ray quality instead :D. It seems like most people just want something quick to turn on in the background than something to really sit down and bask in every detail of.
Yeah, and that leads to the DRM'd content in YouTube (like Movies & TV) not working for me in Kagi on Linux. Unless you're saying I've done something wrong and it really is working for you... in which case I may have some tinkering to do to find out what I did to break it :D.
One correction to my message above: apparently Chrome on Windows is still 720p for Netflix, it was Edge that had 4k support. Or you can install the Netflix App on Windows too.
It's really really hard to give them the benefit of the doubt at this point.
reply