Hacker Newsnew | past | comments | ask | show | jobs | submit | b7894's commentslogin

Gemini 3.0 Pro (or what is deemed to be 3.0 Pro - you can get access to it via A/B testing on AI Studio) does a noticeably better job

https://x.com/cannn064/status/1972349985405681686

https://x.com/whylifeis4/status/1974205929110311134

https://x.com/cannn064/status/1976157886175645875


It was Google that featured a bicycling pelican in a presentation a few months back:

https://simonwillison.net/2025/Jun/6/six-months-in-llms/#ai-...

So I think the benchmark can be considered dead as far as Gemini goes


There’s obviously no improvement on this metric and hasn’t been in a while.


How do people trigger A/B testing?


As far as I can tell they just keep on hammering the same prompt in https://aistudio.google.com/ until they get lucky and the A/B test triggers for them on one of those prompts.


That 2nd one is wild.

Ugh. I hate this hype train. I'll be foaming at the mouth with excitement for the first couple of days until the shine is off.


The game GTA San Andreas was the last major 3D GTA game of the PS2 era. It was the first one to introduce a flyby mechanic, whereby planes, identical to the ones pilotable by the player, and flown by in-game AI, would periodically fly over as an environmental detail. However, due to many different reasons mentioned throughout the video, these planes would often unexpectedly crash into obstacles, sometimes exploding right next to the player. Many attempts were made during the game's development to eliminate these plane crashes, but due to the complexity of the map, the PS2's hardware limitations, oversights and limited development time, the issue made its way onto the final game.

Personally, I find it really cool that something this relatively minor feature in a 20-year-old is being broken down in such detail in this fashion.


Works only on Desktop Edge. Jailbreaks for chat bots have been around for a while now, but this one cleverly used the web page context that Bing can access as a way to inject a prompt.


https://gtaforums.com/topic/669045-silentpatch/

Take a look at the featured fixes for GTA SA, for instance. Fixes many game-breaking bugs while adding support for modern hardware (16:9 resolutions, newer Windows versions, etc.), as well as fixing many other smaller problems with the game. I find it essential to playing the game.


SilentPatch is incredible. GTA San Andreas goes from being a janky mess that hardly (if at all) works on modern hardware to being better than the official "remaster."


To be fair, even the janky old version of San Andreas is better than the remaster. That abomination should never have seen the light of day.


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

Search: