The problem is not the part involving the car (even if the idea of seeking the incidents is lame). The problem is the characters and their interactions. Movies are all about that. Good movies at least, and this sucks.
Jesus, I did the error of watching F1 (the movie with Brad Pitt). How it is possible to let people that are totally clueless write the script? The script is pure poo: it is a terrible movie, totally terrible. A lot of money and efforts to produce something so lame.
Nope, non distributed app running on Redis, with a strict no-profit manifesto, designed to have potentially a rolling team as old members exist the team to keep it running, and so forth. Open source of course.
Opus 4.7 criticizing work done with GPT 5.4 and getting everything wrong. GPT 5.4 critique to the original claims are all spot on matching the errors that I outlined here.
Most tragic things about AI: the folks who should push for democratization of AI tools, which is the real battle, are too focused on denying AI itself to do that. There are many potential issues (and wins), but frontier models available only to the rich is one of the worst.
I really want to fix HN and provide something that is not bound to a specific company.
In the next months I'll provide you with a Hacker News replacement that I'll run myself and I'll guarantee personally: no benefit for whatsoever individual, a team of 10/20 persons since the start, from different time zones, clear rules, total transparency, and a "karma" system.
Note that you can paginate with "More" and never see the post, so it is internally flagged in order to never show up regardless of ranking.
Eventually it will reach the home page as it normally happens, but initially there is always this inertia when the post is in my blog, not sure what broken stuff creates this situation, but trust me: it feels like HN is internally gamed.
HN shadowbanning is always cool. 6 upvotes in 17 minutes but no way it can reach the home page, while 4 votes in 25 minutes is there. Note that I don't ping any friend when I post, so all the votes I receive are spontaneous. Yet... Moderation system and broken algorithms are part of HN decline.
TLDR: no, GPT OSS 120B can't find the OpenBSD bug. I tried systematically, wrote a thread in X. TLDR: it hallucinates where the problem could be about bound check / potential overflow *without* understanding the actual bug and how to trigger it. Even if you give it the offending function and hits.
Here it is better indeed, but the AI conversation is happening elsewhere because here the AI-adverse folks created a situation where this place could not be used in a relaxed way for this goal. This was a dramatic error. So everybody is back on X now.
1. Musk is terrible, let's move to BlueSky!
2. Then people started to migrate back.
3. Who needs to inform a community, needs to stay there as well, and slowly a post there started to be back at 10x reach.
4. Many great folks now are just here... and can't counter the X fascist side.
5. Badsituation
There are people that imbarassed by the LLM advancements compared to their skeptical positions, to save their careers are doing the worst things: going against past colleagues, claiming the agent tools to search into files is symbolic reasoning (I laugh so hard), and even more.
The Linux kernel AI guidelines are the first sane that I read. It is not a coincidence. Where high level work is done, high level work is pretended, regardless of the tools. github.com/torvalds/lin...
Video of bug hunting using LLMs with Redis (but the same pipeline can be used with everything). English audio available, if you click on the YouTube settings, also subtitles.
www.youtube.com/watch?v=opou...
Nahhh... it's better to pay. So you are free to say whatever you want without limits.
In case of doubts, DISCLAIMER: I and @OpenAI are not affiliated and any way. I don't know anybody there. If I say that GPT 5.4 is good, is because I love code, human written code, LLM written code, code written by machines & humans together. So I love good tools about code.
Yep. In the case of Redis installations, mostly they are private stuff where the attacker can't AUTH or even access to the socket for most of the times. So will be relevant for who left instances running on the internet, which is already a security unconscious way to handle things :D
Security in the AI era... GPT 5.4 xhigh work. Screenshot from the Redis core team chat. @valkeyio.bsky.social
I guess we need to coordinate some release.
About (not using) MCP
Then: "LLMs can put together different ideas they saw, not more", then "they work only on provable domains", and so forth. The huge disservice those AI researchers did to the AI safety goal is hard to estimate, but is surely huge.
Every month updating their POV, of course... chasing the mounting evidences. They started with "just a statistical models", then upgraded to "limited reasoning capabilities, no true model of what they are doing"
The fact that we reached Mythos (but even GPT5.4 level) automatic vulnerability search not ready for it is, in part, thanks to the AI researchers that didn't just understand LLMs potential, but actively convinced the masses of their limits.
Follow me on this: if Mythos benchmark numbers and model card info is correct (which I have little reasons to doubt), Anthropic can easily synthesize a better Opus, given they don't want to release Mythos. So, I bet we'll soon see Opus 4 at the level of GPT 5.4 or greater.
One of the most powerful automatic coding (autocoding) trick that almost nobody uses: "Create this new project as specified in SPEC.md using as guide for coding style, design sensibility, comments, ..., the code at /foo/bar/". Style transfer is very powerful.
I'm still trying to post stuff here. But people seem to have moved back on X, regardless of the terrible ownership. At least, Bluesky should try to give some real advantage in the product side, but the strict character limit alone is already discouraging.
Super odd that the Gemma 4 release highlights specifically the ELO score: the least meaningful benchmark ever. We should ask AI labs to stop doing this thing.
I bet the small Gemma 4 models are going to kill all the specialized ASR models for audio to text transcription tasks.