Alifatisk

> GPT-Rosalind-6 uses the same weights as GPT-6 Astra, our flagship reasoning model.

Didn’t Sol-6.1 top Astra? Or is it maybe that Astra is still a larger model and therefore can comprehend deeper complexity better in the long run?

> These people have arguably contributed nothing to society for over a decade […] they’re being praised for being the example of best engineers.

React? We can all criticize it, but it has revolutionized the web. Llama. Did you forget what sparked the whole open-weight wave? It was that. I dislike Meta, but I would not criticize the engineers competence. They have done impressive things, check out their blog if you genuinely are curious.

I guess the point with this to facilitate usage of IPv6.

Is anyone using the vscode extension of Codex? Its insane how brittle it is.

Just a couple of days ago, it was completely broken for about a week before it got somewhat fixed again. When I say fixed, I mean basic functionality is working again but bugs and regressions are still left. There are multiple issues tracking the same problems. The community have even started to patch the extension themselves as a workaround until its adressed.

You know whats even crazier? There are like a new release every other day with lots of commits and changes, yet it still in a bad shape. I have turned off autoupdate for Codex extension for this reason. The only extension I’ve had to.

I mean, it doesn’t take that much work to have some tests in the pipeline to make sure the extension continue to work, it almost feels like they are purposely doing this.

I have now experienced the consequences of ”move fast and break things”. I realize how much software quality means to me. Its not fun being on the receiving end, especially when it affects my daily workflow.

If any of you, see anyone hype up LLMs again, please refer them to the state of Codex vscode extension.

Reminds me of the Vibe.d web framework for D lang. Good memories.

Its incredible how much changes Mandani is doing to benefit the citizens. I start to wonder what the prior mayors was even doing.

You gave me a good laugh, cheers!

Astra*

The novelty isn't binary patching itself. Its the the barrier to entry. Manually locating an bug in compiled code and calculating offsets used to require good skills and knowledge in the domain. Here, someone described the symptoms in a prompt (reminder, still plain English) and got an binary patch without touching a disassembler. To me, that's unbelievable.

Does anyone have insight into the sudden trend of game decomm / recomp and mashups like Minecraft in GTA, Mario in Skyrim, Cod in Life is Strange, Among us in Portal 2 and so on? What triggered it? Is there a specific new tool, technique or LLM that sparked this interest? I am curious.

Demo on iPhone 17 https://nitter.app/c22_dev/status/2108572247539544459

The Chinese labs aren’t constraining their models as much as Western labs do. That’s why HF used GLM. If you remember the early times with how Gemini (Bard then) and Claude refused almost everything, you’d despise the idea of guardrailing. (Its important in some areas though)

That’s unbelievable. To be able to locate and fix bugs by patching the binary.

Cmon, there is more space for a better descriptive title than just putting the domain there.

I gotta admit, I love how their design system and how they market things. It looks so good. However the true state of their toolings is closer to a burning dumpster fire. If you look at Codex Github repo for example, the amount of existing issues and continuously new issues appearing while tagged releases is being spewed out. Its truly a nightmare. Their vscode extension has been broken for almost 1 week now, if not more. Its instead a community effort to repair it.

Does this fall under the Tetris effect?

These prices are getting ridiculous, we’re talking about 180$ / month here.

Worth mentioning, this has nothing to do with the Python Software Foundation, their domain is at python.org

I understand why would would move Pro variant behind paywall, you don’t get many uses of it anymore on free tier. But moving the Flash version behind paywall is kinda crazy.

Did we forget what Flash was meant for? I have tried Flash-lite, in my tests, almost all the recent models we have today are good and enough for most daily tasks.

Flash-lite is one of the few models available that is easy to notice its flaws. Its good to summarize data (for example search results), that’s it.

You should probably link to the relevant post

https://github.com/streetcomplete/StreetComplete/issues/5421...

Yup, GPT-5.6 Luna was a checkpoint for me. Too good for its price.

> the cache read discount rises from 90% to 95%. GPT-6.1 Sol’s overall blended price for agentic workloads is therefore slightly lower than GPT-6 Sol. This represents an additional price cut, following GPT-6 Sol’s original 50% discount from GPT-5.6 Sol

Wow, just wow. We are racing to the bottom with these prices.

Where was this confirmed?

> I also started building AI into how I hunt, which led me to develop Antares, my personal AI hackbot.

Don't be a meat proxy

I guess they released this because GPT-6 Sol was underwhelming, they didn't even release it to ChatGPT. It was basically GPT-5.6 Terra for the price of Sol. However, who doesn't like price cuts? Astra for the fifth of the price? Wow, OpenAI have been quite generous recently, I still have not forgotten their 90% price cut with GPT-5.6 Luna, and now this? Astra was truly a milestone, and now they are offering similar "intelligence" for cheaper price. Incredible.

One thing I wish was better communicated is the mileage we get for our subscriptions. I do not fully understand how much usage I get with each model and their reasoning effort on 5h and weekly limit in Codex. I am asking because I know switching to Astra would consume my 5h usage limit quite rapidly, so I avoid it. If I knew how much mileage I would get from each model and respective reasoning effort, then I would be able to plan my workflow better and know when to upgrade model for a task. In almost all cases, GPT-6 Luna (XHigh) have been enough. That's why I appreciate its discount, because its dirt cheap, yet highly capable.

In other news:

> In the coming days, we’ll also offer GPT‑6.1 Sol Ultrafast , with up to 8x faster token generation compared to its standard speed in Codex.

Other comments have already addressed this.