This is a problem for the employer and for the selection and remuneration of staff (at all levels of the chain and not just those in contact with the customer)
I have the opposite experience with codex 5.3 I had to use 5.2 to design and 5.3-codex to execute , while 5.4 was a better in both, and 5.5 ( all used xhigh) is even better
Just because it's not important to pay attention to CVEs, why not waste the readers' time by creating "fictional" CVEs without a disclaimer in the first line? Just because it's not already difficult to scrape through the information and noise on this internet...
especially if it appears on the front page of hackernews
Have you not read CVEs as of late? As a precondition for getting their funding back, all the doge boys get to write the CVEs for their own orgs. Insane parentheticals about trans people is the norm now.
I saw a comment very similar to this on a blog post testing the Copy Fail exploit, where someone was complaining that without a tl;dr at the top, it took too much effort for them to find out whether the blog post documented a new exploit. In fact, reading less than a paragraph already showed that couldn't be the case; the table of contents is enough.
If a glance at the CVE number that isn't a number doesn't do it, a minute or less of skimming this article likewise reveals it to be satire on a blog that's actually pretty thoughtful when it comes to supply chain attacks.
Idk how else to characterize this except as a literacy problem. Learn to skim. It should be unacceptable to characterize a few minutes of reading as unbearable toil. If your time is really so precious that (although you can surf Hacker News) you can't spare 1-3 minutes to read, surely you have someone else to whom to delegate the responsibility of watching for supply chain attacks.
I believe that as soon as nuclear fusion becomes operational (and perhaps AI could be of great help in this regard in the next 5 years),
all the carbon storage methods (efficient and otherwise) studied so far could be immediately put into action.
In addition to the immediate reduction in the use of fossil fuels for energy production, the scenario could be completely changed in 10 years, water could be desalinated, desertification reversed, etc.
Free and unlimited energy would be the solution to everything. The question is whether we will get there before it's too late... and perhaps AI is the answer?
1. it's 1.5x , it's quite fast for the level of thinking it has
2. no if you are on subscription, it's the same, at 20$ codex 5.4 xhigh provide way more than 20$ opus thinking ( this one instead really can burn 33% with 1 request, try to compare then on same tasks ) also 8x .. ??? if you need 1M token for a special tasks doesn't hit /fast and vice-versa , the higher price doesn't apply on subscription too..
3. false, i'm on pro , so 10x the base , always on /fast (no 1M), and often 2 parallel instances working.. hardly can use 2% (=20% of 5h limit , in 1h of work ( about 15/20 req/hour) ) , claude is way worse on that imo
imo , the main feature is /fast ... who use 1M context and for what? the model become dumber already at 200K.. it's better to manage the context , and since 5.3, codex is very good at managing it