As an engineer I’d be impressed and would put you up to the top of the pile
Sadly I don’t run the company, and as a hiring manager that’s a great way to reduce my shortlist. We can’t have people like myself who ignore corporate policies.
there seems to be at least one service that your LLM can find if it searches the internet (e.g. in my case "best rental API") that poisons your context into thinking that that one service is the definitive and only available API for that data
1. Not today. November 2025. They don't make it clear.
1.1. One would expect that to be put in the title, when the article is written almost a year after that.
1.2. No, the article doesn't state that in the first paragraph. Posting in it full seem to be the only way to fend off lazy comments:
In November 2025, Earth was buffeted by several massive eruptions of solar material that slammed into the magnetosphere.
That's it - the whole paragraph. Several paragraphs later - GPS first mentioned. No clear links between dates stated.
2. It is unclear what is the source of the claim.
UPD: Commenter below found the source, but TFA doesn't make a good job of presenting that as a source of the 33 feet glitch claim, but rather posts another citation from it.
They should've just quote this and be done with it:
During the storm main phase, an east–west elongated band of intense auroral brightness expanded equatorward, producing a horizontally extended strip of strong density gradients that favored the development of small-scale irregularities. These small-scale irregularities triggered pronounced amplitude scintillations (S4 > 0.5) and caused significant positioning errors exceeding 10 m—large enough to disrupt GNSS-dependent applications across CONUS for hours, particularly precision agriculture and autonomous transportation industries. [1]
3. Navigation issues happened before, they state it right there. They were more disruptive as well.
4. The author has articles all over the topics. Everything is sensationalized.
5. Every presented link seem to have this awful Cloudflare js challenge.
Bad article overall.
P.S. Response to the false claim below - no, there's nothing about GPS in "the first 3 words of the article".
Wouldn't think I'd be cheering Antrophic decision, but this is excellent.
They probably were thinking about how that serves them as an ad, not about transparency, but still.
I say they should go one step further and somehow make it harder/inconvenient to turn it off (big tech is good at this already, so...); or, maybe, hide that option behind extra feature under premium subscription or something.
P.S. The comments are pure gold. They don't like they can't fake authorship and have the audacity to be indignant!
As a Claude user this is just a benefit to me. Means I can grab the session and resume if I ever see a commit I want to jump back into, and Claude can read these sessions itself whenever I reference the commit, which helps a bunch.
It might come with advertising benefits for them but expect it’s mostly just because it helps their tools work and that benefits everyone.
Since the update is done semi-automatically by the means of AWS RDS, does AWS takes any responsibility for that? Unless this use case is warned against in migration notes, I would think they ought to.
reply