Hacker Newsnew | past | comments | ask | show | jobs | submit | yalok's commentslogin

for Google AI Overview (not sure which Gemini model is used for it, must be something smaller than regular model), looks like search/RAG helps it get it right - since it relies on LinkedIn and Hacker News (!) posts to respond correctly...

as of Feb 16, 2026:

====

Drive the car. While 50 meters is a very short distance, the car must be present at the car wash to be cleaned, according to LinkedIn users [1]. Walking would leave your car at home, defeating the purpose of the trip, notes another user.

Why Drive: The car needs to be at the location to be cleaned. It's only a few seconds away, and you can simply drive it there and back, says a Hacker News user. [2]

Why Not to Walk: Walking there means the car stays home, as noted in a post. [3]

The best option is to start the engine, drive the 50 meters, and let the car get washed.

[1] https://www.linkedin.com/posts/ramar_i-saw-this-llm-failure-... [2] https://news.ycombinator.com/item?id=47034546 [3] https://x.com/anirudhamudan/status/2022152959073956050/photo...

But the regular Gemini reasons correctly by itself, without any references:

==== Unless you have a very long hose and a very patient neighbor, you should definitely drive. Washing a car usually requires, well, the car to be at the wash. Walking 50 meters—about half a New York City block—is great for your step count, but it won't get your vehicle any cleaner! Are you headed to a self-service bay or an automatic tunnel wash?


in ~30 years of my work in DSP domain, I've seen insane amount of ways to do signal processing wrong even for simplest things like passing a buffer and doing resampling.

The last example I've seen in one large company, done by a developer lacking audio/DSP experience: they used ffmpeg's resampling lib, but, after every 10ms audio frame processed by resampler, they'd invoke flush(), just for the sake of convenience of having the same number of input and output buffers ... :)


Haha wow, I guess that gives a very noticeable 100 Hz comb-like effect... noone cared to do a quick sanity check on that output?!

this. Deep understanding of physics involves building a mental model & intuition how things work, and the process of building is what gives the skill to deduce & predict. Using AI to just get to the answers directly prevents building that "muscle" strength...

their Play store review practices are such a joke. Apps review is a completely obscure process, no clear way to see that the app is in review state, if they reject - amount of information why it was rejected is minimal and you have to second-guess; appealing is not trivial; most of the reviews are done by AI which gets triggered in totally random places from time to time (e.g., in my case, some pictures which looked fine for kids for years and went through many previous reviewed, suddenly seem too violent).


I have healthcare apps. The review process for me consists of some reviewer deciding what set of healthcare features I should have picked from their list and rejecting on that basis. But subsequent reviewers have different opinions. In one app version release I got rejected 5 times for picking the wrong set of healthcare features as either the reviewer changed their mind or I got different reviewers. The app has been on Google play for 13 years.


In my experience, anything related to Google Ads - they never reacts to any claims of scam…

Their incentives contradict healthy behavior… :(


is there any good comparison of Hybrid vs EREV efficiency (when main battery is depleted), even with Atkinson cycle ICE for EREV? my understanding was that the main reason for all this complexity in Hybrids was due direct-to-wheel power transfer efficiency, while in EREV there's efficiency loss when converting ICE output to electric current...


Looking to the Chinese market is insightful, IMO. There's one platform for a luxury sedan, and it gets ~200mi on EV mode (~100MPGe) and then ~400mi on gas. It works out to about 70mpg purely on gas. I'm not sure how it's so high, but I'm guessing a combination of low drag (Cd), efficient small turbocharged engine (you really only need enough power maintain high speed, not accelerate up to it), and lots of regen braking.

BYD and Geely have similar systems. Their ICE are around 47% thermal efficiency so like ~double what you'd expect in a pure ICE car + regen and other bonuses.

https://carnewschina.com/2025/08/02/im-motors-launches-stell...


how large are the STT and LLM models that you use on-device? are they part of the OS or downloaded with the app?


There are several different options you can pick from between 50MB and 600MB.


thanks! are any of them multi-lingual? what languages may be supported?


extremely telling - lot's of tech mentioned there either never reached expected potential or completely obsolete...

Prompts to be much more cautious with the current tech, and invest more time in fundamental stuff (like closer to science).


moonlighting is permitted by law in California (companies legally can't prevent you from doing it, iiuc), as long as there's no conflict of interest with your main job...


"no conflict of interest" is basically meaningless if your day job is writing software. These clauses you sign are quite broad in what that scope of conflict could be.

Every company I've worked for has had very explicit rules that say, you must get written permission from someone at some director or VP level sign off on your "side project," open source or not.

You might want to check your company guidelines around this just to make sure you're safe.


Side projects that aren't a conflict of interest when working at Google is rather limiting. Likely less so for small companies.


Not really, in my personal experience and per my friends, most of big companies are pretty lenient about it, except for Apple.


No, they're pretty strict. It just changes what you are allowed to do, with Apple being very restrictive in not letting you do it at all.


As long as you don't use their hardware to do it.


that goes without saying, but it's still not free permission when you use your own stuff.


add to it multiple iterations of having to restart pretraining from some earlier checkpoint when loss plateaus too early or starts increasing due to some bugs…


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: