Sabitlenmiş Tweet
sneak peek at @edgefoundxyz new desktop app.
Building a setup on $BTC.
high => low => sweep the low => reclaim ema 10
English
guybedo
6.5K posts
guybedo
@guybedo
📈 @edgefoundxyz https://t.co/fGwhDfPsgl trading alerts + backtests 🔧 https://t.co/a4K5jYOju1 ai powered productivity
Katılım Mayıs 2009
850 Takip Edilen534 Takipçiler
Couple of Antigravity updates going into the long weekend...
- 2x'ed max context length for Gemini 3.5 Flash in AGY
- AGY 2.0 <> AGY IDE clearer in app
- Major bug fixes (esp on Windows)
- Another quota reset today
Thanks for the feedback and excited to see what you all build!
Varun Mohan@_mohansolo
Thanks for all of the Antigravity feedback over the last couple of days, especially around the IDE. Our intention was never to remove the IDE support for developers, and we should have been clearer with that in the product from the beginning. We’ve made it clearer in 2.0 on how to connect to the IDE, fixed issues with opening the IDE on Windows machines, provided instructions to restore IDE settings & extensions, and more. New releases for the Antigravity IDE and Antigravity 2.0 have rolled out with these changes. We should have done better so we’re going to reset everyone’s Gemini quota for the week again.
English
guybedo retweetledi
@_mohansolo I'd love to try Antigravity Cli, but i can't, although i'm a Google AI subscriber.
Google still doesn't know French Polynesia is in FRANCE, why are we still being gated ?
x.com/guybedo/status…
guybedo@guybedo
i'm really tired of this location gating. I'm a Google AI subscriber, i live in France (French Polynesia), and yet i can't use the cli because of location restriction. Is somebody at Google going to finally realize French Polynesia is in France ? How can i be a Google AI subscriber and yet be excluded at the API level .... ? agent executor error: FAILED_PRECONDITION (code 400): User location is not supported for the API use.: FAILED_PRECONDITION (code 400): User location is not supported for the API use. FAILED_PRECONDITION (code 400): User location is not supported for the API use.: FAILED_PRECONDITION (code 400): User location is not supported for the API use.
English
Thanks for all of the Antigravity feedback over the last couple of days, especially around the IDE. Our intention was never to remove the IDE support for developers, and we should have been clearer with that in the product from the beginning.
We’ve made it clearer in 2.0 on how to connect to the IDE, fixed issues with opening the IDE on Windows machines, provided instructions to restore IDE settings & extensions, and more.
New releases for the Antigravity IDE and Antigravity 2.0 have rolled out with these changes.
We should have done better so we’re going to reset everyone’s Gemini quota for the week again.
English
i'm really tired of this location gating.
I'm a Google AI subscriber, i live in France (French Polynesia), and yet i can't use the cli because of location restriction.
Is somebody at Google going to finally realize French Polynesia is in France ?
How can i be a Google AI subscriber and yet be excluded at the API level .... ?
agent executor error: FAILED_PRECONDITION (code 400): User location is not supported for the API use.: FAILED_PRECONDITION (code 400): User location is not supported for the API use.
FAILED_PRECONDITION (code 400): User location is not supported for the API use.: FAILED_PRECONDITION (code 400): User location is not supported for the API use.
English
Antigravity CLI 1.0.1 is out.
Key updates:
- Fixed OAuth not persisting in some environments.
- Enhanced the visual experience on Windows.
- Added the new "proceed in sandbox" permission control.
Restart agy to auto update or run “agy update".
See the full changelog for details:
github.com/google-antigra…
English
@antigravity i can't even exit this thing ffs.
ctrl+c doesn't do anything
English
trying out @antigravity cli, looking good so far.
It looks like i'm gonna do some serious work here.
GIF
English
@MoonshotAi Kimi K2.6 seems to be on the slower side though.
I'm using it on less urgent stuff, it works well and it's less expensive than Claude or Codex.
It's a good deal
English
I've been working exclusively with Claude Code and Codex for a few months.
I'm now giving @MoonshotAI Kimi K2.6 a try and it looks good so far.
Initially i tried forgeCode but it seemed super verbose and it looked like the model was running in circles.
Then i switched to OpenCode and the experience is quite good.
OpenCode's UI is good actually, and as a harness it seems to be way better than forgecode, kimi is doing a good job so far.
Latest gpt 5.5 model is really good and it made me switch most of my workload to codex. Maybe i can definitely move away from Claude and replace it with Kimi K2.6 alongside Codex/Gpt
English
@nottombrown @SpaceX @elonmusk It looks like SpaceX doesn't have a use for its Colossus 1 & 2 datacenters.
I thought they had an AI division and a LLM, what was it again? grok ?
English
We’re expanding our partnership with @SpaceX, and will be scaling up on GB200 capacity in Colossus 2 throughout June.
Appreciate @elonmusk and the team helping us find good homes for the Claudes.
Tom Brown@nottombrown
In the next few days we'll be ramping up Claude inference on Colossus. Grateful to be partnering with SpaceX here. We are going to need to move a lot of atoms in order to keep up with AI demand, and there's nobody better at quickly moving atoms (on or off planet Earth)
English
"This is a general-purpose LLM. It wasn’t targeted at this problem or even at mathematics. Also, it’s not a scaffold. We have not pushed this model to the limit on open problems"
OpenAI@OpenAI
Today, we share a breakthrough on the planar unit distance problem, a famous open question first posed by Paul Erdős in 1946. For nearly 80 years, mathematicians believed the best possible solutions looked roughly like square grids. An OpenAI model has now disproved that belief, discovering an entirely new family of constructions that performs better. This marks the first time AI has autonomously solved a prominent open problem central to a field of mathematics.
English
"This is a general-purpose LLM. It wasn’t targeted at this problem or even at mathematics. Also, it’s not a scaffold. We have not pushed this model to the limit on open problems"
Thomas Bloom@thomasfbloom
An internal OpenAI model has disproved one of the most well-known Erdős problems: the unit distance problem. This is, without doubt, the most impressive achievement of AI in mathematics so far. openai.com/index/model-di…
English
@scaling01 yeah gpt 5.5 medium works pretty well for most coding tasks.
English
My definition of model intelligence has been very clear over the past two years.
For me the sign of an intelligent model was always good results with as few resources as possible, which is why I was a big fan of Sonnet 3.5/3.6 and Opus models. These models would just get things and one-shot problems "without thinking".
On the other hand I really disliked reasoning models from o1-preview up until o3, because it just wasn't worth it back then and felt like inelegant brute-force slop. You would get slightly better results for 10x the cost.
Later from GPT-5 up to GPT-5.2 the reasoning budgets exploded from a few thousand tokens to 50-100k tokens.
Since then reasoning efficiency has only improved, and we are now living in a world where GPT-5.5 and Mythos get insane results with very low reasoning budgets and where higher token budgets feel worth it.
I think part of this is also that models nowadays know how much reasoning to spend on each problem. So when you set reasoning effort to xhigh it doesn't think for 100k tokens on a very easy problem just for the sake of the xhigh setting.
(but personally I still use medium thinking budget like 90% of the time and will only go up to xhigh when the tasks have a high enough skill ceiling. it's overkill to use xhigh for everything)
English
@sama maybe this time don't update the next reset date because if you're doing that again, you're just screwing our remaining tokens like you did last time
x.com/guybedo/status…
guybedo@guybedo
So OpenAI just reset again the limits, it'smeant to give credits to people but in the end we're just losing tokens. I had 30% left until tomorrow and then onto my new weekly cycle. Now i have 78% left and my new weekly cycle starts on 23rd. => screwed of 30% @thsottiaux @OpenAI
English
if this tweet gets 1 like, tibo will reset codex rate limits
English
@thsottiaux i'd love an update on this.
Because of the limits reset, i basically lost 30% of my weekly limit.
x.com/guybedo/status…
guybedo@guybedo
So OpenAI just reset again the limits, it'smeant to give credits to people but in the end we're just losing tokens. I had 30% left until tomorrow and then onto my new weekly cycle. Now i have 78% left and my new weekly cycle starts on 23rd. => screwed of 30% @thsottiaux @OpenAI
English
@fcoury instead of having 30% until 18th and then 100% until 25th, i'm now in a new cycle until 23rd, i'm at 78%.
So basically i lost my 30% i had until tormorrow.
x.com/guybedo/status…
guybedo@guybedo
So OpenAI just reset again the limits, it'smeant to give credits to people but in the end we're just losing tokens. I had 30% left until tomorrow and then onto my new weekly cycle. Now i have 78% left and my new weekly cycle starts on 23rd. => screwed of 30% @thsottiaux @OpenAI
English
Limits should be recovering. If yours is back to normal let me know please.
English
@thsottiaux i know you meant well but in the end we're just losing some tokens.
x.com/guybedo/status…
guybedo@guybedo
So OpenAI just reset again the limits, it'smeant to give credits to people but in the end we're just losing tokens. I had 30% left until tomorrow and then onto my new weekly cycle. Now i have 78% left and my new weekly cycle starts on 23rd. => screwed of 30% @thsottiaux @OpenAI
English
Codex usage limits are back to normal. For ~2 hours we had some issues where the enforced limits were wrong for the majority of users on a subscription.
We waived usage consumption for that time and things should be set again to exactly to where you left it.
Back to codexing.
Tibo@thsottiaux
Seeing issues where usage limits are out of sync for some Codex users. Apologies and team is investigating.
English