Hacker News: crorella

New comment by crorella in "Ferrari Luce"

crorella — Tue, 26 May 2026 04:03:50 +0000

I had the same visceral reaction lol, so ugly.

New comment by crorella in "Uber’s COO says it’s getting harder to justify money spent on tokenmaxxing"

crorella — Mon, 25 May 2026 17:25:22 +0000

Tokenmaxxing makes no sense, it is akin to write extremely inefficient SQL / Spark Jobs, full of cartesian joins, ultra skewed datasets, etc, just for the sake of using as much compute / memory / IO as possible.

This always happens when the metric becomes the goal, companies should nurture and foster an environment where AI is used in the most efficient way possible, first asking "do we really need an agent for this" and if so, what kind of agent is needed, what model, reasoning level, etc.

They should also promote projects that aim at saving tokens, increasing cache hits, codifying the information in ways such they use as less context as possible (graphs of knowledge are pretty good for this!)

New comment by crorella in "Google changes its search box"

crorella — Tue, 19 May 2026 20:17:45 +0000

what a weird surface to put LLMs

New comment by crorella in "New Lifetime Plex Pass Pricing"

crorella — Tue, 19 May 2026 15:57:51 +0000

Same! At first I was wary of using it because the UI looked less polished, but from the start the stability has been vastly superior and now the UI is much better too.

as a bonus, I have a old version Emby Theather (the windows form based one) that plays 4K with no issues on my computer unlike browsers that fail at that.

New comment by crorella in "Every AI Subscription Is a Ticking Time Bomb for Enterprise"

crorella — Sun, 17 May 2026 16:54:15 +0000

wouldn't move to local models in the future remove part of that risk for companies?

Daybreak Frontier AI for cyber defenders

crorella — Mon, 11 May 2026 18:01:27 +0000

Article URL: https://openai.com/daybreak/

Comments URL: https://news.ycombinator.com/item?id=48098377

Points: 11

# Comments: 1

New comment by crorella in "GPT-5.4"

crorella — Fri, 06 Mar 2026 07:04:44 +0000

underrated comment, this is going to be the main differentiator going forward, the more powerful and versatile harness the more the models will be able to achieve and better/more advanced products will come out of it.

New comment by crorella in "Codex for Windows"

crorella — Wed, 04 Mar 2026 17:59:53 +0000

* Parallel agents: Run multiple coding tasks at once so you can move faster across projects

* Isolated workspaces: Each task runs in its own worktree so changes stay organized and conflict-free

* Review changes: Inspect diffs and proposed edits before applying them to your codebase

* Stay in flow: Switch between tasks without losing context or progress

* Automate workflows: Reuse repeatable tasks with configurable skills

* Works with your tools: Open changes in your editor and integrate with your existing setup

* Track progress: Follow what each agent is doing in real time

* Windows sandboxing: Run agent mode inside an OS-level sandbox, with bounded permissions and explicit approval for escalation

* Ship faster: Move from idea to working code with less overhead

Codex for Windows

crorella — Wed, 04 Mar 2026 17:59:53 +0000

Article URL: https://apps.microsoft.com/detail/9plm9xgg6vks?hl=en-US&gl=US

Comments URL: https://news.ycombinator.com/item?id=47251296

Points: 2

# Comments: 1

New comment by crorella in "Dan Simmons, author of Hyperion, has died"

crorella — Fri, 27 Feb 2026 22:11:33 +0000

I am sad to know about this, Dan Simmons had a mind blowing amount of imagination and the ability to turn that into interesting and imaginative books that expanded my imagination when I read them.

I loved Hyperion cantos, Illium and then non sci-fi books like A Winter Haunting and Summer of night (which I read in the wrong order lol).

I am also happy to read that he was a great person overall and a great teacher. May he rest in peace.

New comment by crorella in "I’m joining OpenAI"

crorella — Sun, 15 Feb 2026 22:33:35 +0000

Welcome :D

New comment by crorella in "GPT-5.2 derives a new result in theoretical physics"

crorella — Fri, 13 Feb 2026 19:31:47 +0000

The preprint: https://arxiv.org/abs/2602.12176

New comment by crorella in "GPT-5.3-Codex"

crorella — Thu, 05 Feb 2026 19:17:18 +0000

The variety of tasks they can do and will be asked to do is too wide and dissimilar, it will be very hard to have a transversal measurement, at most we will have area specific consensus that model X or Y is better, it is like saying one person is the best coder at everything, that does not exist.

New comment by crorella in "GPT-5.3-Codex"

crorella — Thu, 05 Feb 2026 18:13:50 +0000

The thrill of competition

New comment by crorella in "Unrolling the Codex agent loop"

crorella — Fri, 23 Jan 2026 21:23:45 +0000

Same here! I think it would be good if this could be made by default by the tooling. I've seen others using SQL for the same and even the proposal for a succinct way of representing this handoff data in the most compact way.

We used Codex to build Sora for Android in 28 days

crorella — Sun, 14 Dec 2025 04:55:09 +0000

Article URL: https://openai.com/index/shipping-sora-for-android-with-codex/

Comments URL: https://news.ycombinator.com/item?id=46260840

Points: 2

# Comments: 1

New comment by crorella in "GPT-5.2"

crorella — Fri, 12 Dec 2025 03:06:43 +0000

what I had in mind when I added that comment was for coding, with the use of .md files. For the web version of chats I agree there is little control on how to tailor the way you want the agent to behave, unless you give a initial "setup" prompt.

New comment by crorella in "GPT-5.2"

crorella — Thu, 11 Dec 2025 23:07:17 +0000

It’s like having 3 coins and users preferring one or the other when tossing it because one coin gives consistently more heads (or tails) than the other coin.

What is better is to build a good set of rules and stick to one and then refine those rules over time as you get more experience using the tool or if the tool evolves and digress from the results you expect.

New comment by crorella in "Ovi: Twin backbone cross-modal fusion for audio-video generation"

crorella — Wed, 22 Oct 2025 21:57:57 +0000

At this rate, in a few months we will have probably some high quality shorts entirely generated by this.

New comment by crorella in "Meta Superintelligence Labs' first paper is about RAG"

crorella — Sun, 12 Oct 2025 01:59:40 +0000

Personal experience here in a FAANG, there has been a considerable increase in: 1. Teams exploring how to leverage LLMs for coding. 2. Teams/orgs that already standardized some of the processes to work with LLMs (MCP servers, standardized the creation of the agents.md files, etc) 3. Teams actively using it for coding new features, documenting code, increasing test coverage, using it for code reviews etc.

Again, personal, experience, but in my team ~40-50% of the PRs are generated by Codex.