401–410 of 634 posts
Actually kind of excited for this. I've been using 5.2 for awhile now, and it's already pretty impressive if you set the context window to "high". Something I have been experimenting with is AI-assisted proofs. Right now I've been playing with TLAPS to help write some more comprehensive correctness proofs for a thing I've been building, and 5.2 didn't seem quite up to it; I was able to figure out proofs on my own a b…
Earlier quoted context omitted.
Wouldn't that be illegal ? i.e. cartel to collude like that ?
You were downvoted but I don't understand why. This is the purpose/spirit of antitrust law [1] [1] https://en.wikipedia.org/wiki/United_States_antitrust_law
---
Sadly it was the core of anti-trust law, since 1970s things have changed.
The predominant view today (i.e. Chicago School view) in both judiciary and executive are influenced by Justice Bork's ideas that consumer benefit being the deciding factor over company's actions.
Consumer benefits becomes opinions of projections by either side of a case about the future, whereas company actions like collusion, pricing fixing or M&A are hard facts with strong evidence. Today it is all vibes on how the courts (or executive) feel .
So now we have Government sanctioned cartels like in Aviation Alliances [1] that is basically based on convoluted catch-22-esque reasoning because it favors strategic goals even though it would be a violation of the letter/spirit of the law.
[1] https://www.transportation.gov/office-policy/aviation-policy...
Earlier quoted context omitted.
All shared machine learning benchmarks are a little bit bogus, for a really “machine learning 101” reason: your test set only yields an unbiased performance metric if you agree to only use it once. But that just isn’t a realistic way to use a shared benchmark. Using them repeatedly is kind of the whole point. But even an imperfect yardstick is better than no yardstick at all. You’ve just got to remember to maintain a…
Is an imperfect yardstick better than no yardstick? It reminds me of documentation — the only thing worse than no documentation is wrong documentation.
When such benchmarks aren’t available what you often get instead is teams creating their own benchmark datasets and then testing both their and existing models’ performance against it. Which is eve worse because they probably still the rest multiple times (there’s simply no way to hold others accountable on this front), but on top of that they often hyperparameter tune their own model for the dataset but reuse previously published hyperparameters for the other models. Which gives them an unfair advantage because those hyperparameters were tuned to a doffeeent dataset and may not have even been optimizing for the same task.
Earlier quoted context omitted.
>civilized facade of mutual cooperation >Dirty tricks and underhanded tactics As long the tactics are legal ( i.e. not corporate espionage, bribes etc), the no holds barred full free market competition is the best thing for the market and the consumers.
The consumers are getting huge wins. Model costs continue to collapse while capability improves. Competition is fantastic.
And yet RAM prices are still sky high. Game consoles are getting more expensive, not cheaper, as a result. When will competition benefit those consumers? Or consumers of desktop RAM?
Earlier quoted context omitted.
Converge towards what though... I think the level of testing/verification you need to have an LLM output a non-trivial feature (e.g. Paxos/anything with concurrency, business logic that isn't just "fetch value from spreadsheet, add to another number and save to the database") is pretty high.
in the new world, engineers have to actually be good at capturing and interpreting requirements
Actually kind of excited for this. I've been using 5.2 for awhile now, and it's already pretty impressive if you set the context window to "high". Something I have been experimenting with is AI-assisted proofs. Right now I've been playing with TLAPS to help write some more comprehensive correctness proofs for a thing I've been building, and 5.2 didn't seem quite up to it; I was able to figure out proofs on my own a b…
"High" the the reasoning level. The context window never changes.
Earlier quoted context omitted.
Please no, I don’t need my quick prototypes hardened against every perceivable threat.
In most cases security is not a matter of adding anything in particular, but a matter of just not making specific types of mistakes.
I'm having a hard time parsing the openai website. Anyone know if it is possible to use this model with opencode with the plus subscription?
[0]: https://opencode.ai/docs/ecosystem/#:~:text=Use%20your%20Cha...
[1]: https://github.com/numman-ali/opencode-openai-codex-auth
Earlier quoted context omitted.
I'm personally 100% convinced (assuming prices stay reasonable) that the Codex approach is here to stay. Having a human in the loop eliminates all the problems that LLMs have and continously reviewing small'ish chunks of code works really well from my experience. It saves so much time having Codex do all the plumbing so you can focus on the actual "core" part of a feature. LLMs still (and I doubt that changes) can't…
I'm personally 100% convinced of the opposite, that it's a waste of time to steer them. we know now that agentic loops can converge given the proper framing and self-reflectiveness tools.
You might be able to get away without the review step for a bit, but eventually (and not long) you will be bitten.
Earlier quoted context omitted.
I think it's the opposite. Especially considering Codex started out as a web app that offers very little interactivity: you are supposed to drop a request and let it run automatously in a containerized environment; you can then follow up on it via chat --- no interactive code editing.
Fair I agree that was true of early codex and my perception too.. but today there are two announcements that came out and thats what im referring to. specifically, the GPT-5.3 post explicitly leans into "interactive collaborator" langauge and steering mid execution OpenAI post: "Much like a colleague, you can steer and interact with GPT-5.3-Codex while it’s working, without losing context." OpenAI post: "Instead of w…
I don’t think there’s something deeply philosophical in here, especially as Claude Code is pushing stronger for asking more questions recently, introduced functionality to “chat about questions” while they’re asked, etc.