Idcbtw

@DevBredda @robinebers Clean af

codex just built this for me, an openusage (by @robinebers) fork for linux. what do you guys think? Thinking of releasing it with support to windows and linux and a mobile app aswell.

@pomterree left is fable right is gbt

One of them is Fable, the other GPT 5.6; to realistically recreate Minecraft from scratch. Guess.

@pomterree ig they gona tell opus 4.8 to play smart as the docs say s. mostly 4.8 fall back

FABLE IS BACK BY TOMORROW. I REPEAT.

@DevBredda @MistralAI i thought it was a just a joke

why are we all clowning on Le Chaton Fat by @MistralAI I get its a funny thing but dont be raising my hopes... unfortunately no confirmation that this model will come out or for Mistral to even have something cooking..

or perhaps try out the ai-speedometer cli aispeedometer.live/?view=cli bun i -g ai-speedometer

if you use oss coding plans like ollama cloud , synthetic , minimax , opencode go and want to know the model token speed and other meta data over time . check out aispeedometer.live

understand how other provider token speed feels like on race page . aispeedometer.live/?view=race

Hey guys! A friend of mine create this amazing site for checking out the average TPS for each AI model from most provider. This can finally allow you to see where you can get the best TPS for your favourite model! Any feedback would be appreciated aispeedometer.live

@DevBredda ay lets go :D

@jahirsheikh8 bro it literally has the most usage on openrouter .

Bro disappeared like he never existed.

@ezbaze_ @OpenAI dwag there is oss projects that mogs what ever that is

@OpenAI when will computer-use/chrome be avalible in the EU? :c

Windows users, this one’s for you. Computer use now works on Windows, so Codex can take action on your Windows computer. And with Windows support for Codex in the ChatGPT mobile app, you can start, review, and steer tasks on the go while work continues on your Windows machine. An early experience, but we’re working on more ways to keep your work moving, wherever you are.

@ezbaze_ eat more

i might be addicted x.com/ajambrosino/st…

@ezbaze_ @ryanvogel @opencode cool shi dawg

@ryanvogel @opencode openadmin <3

hey @opencode users we've all seen AI agents play minecraft, but what if one was the ADMIN so i'm making an experimental SMP where the admin is an @opencode agent that can give you stuff and help you progress i'll be streaming regular updates and posting updates on here

@thdxr free marketing ?

just got inside info that openai is working on a new model

gpt image on minecarft builds . just asked it to make something massive .

@ArtificialAnlys @deepseek_ai man why not do decimal places . no way that many models are just tied up

DeepSeek is back among the leading open weights models with the release of DeepSeek V4 Pro and V4 Flash, with V4 Pro second only to Kimi K2.6 on the Artificial Analysis Intelligence Index @deepseek_ai has released DeepSeek V4 Pro and V4 Flash. V4 is the first new architecture from DeepSeek since V3. V4 introduces a new architecture with V4 Pro at 1.6T total / 49B active parameters and V4 Flash at 284B total / 13B active parameters, and is DeepSeek's first two-tier lineup, with Pro positioned for maximum capability and Flash for faster, lower-cost inference. Both models are hybrid thinking/non-thinking. We tested the reasoning variants in Max Effort and High Effort. A year ago, DeepSeek R1 and R1 0528 were the leading open weights reasoning models on the Intelligence Index. Since then, several other open weights labs have released strong reasoning models, and V4 Pro now enters as the #2 open weights reasoning model on the Artificial Analysis Intelligence Index, behind only Kimi K2.6 (54). V4 Pro and V4 Flash remain also text input and output only. Key takeaways: ➤ Large 10 point gain in Intelligence Index: DeepSeek V4 Pro (Max) scores 52 on the Artificial Analysis Intelligence Index, up from 42 for V3.2, making it the #2 open weights reasoning model behind Kimi K2.6. That said, if the weights to MiMo-V2.5-Pro are released as they have been for other Xiaomi models then it will place third. V4 Flash (Max) scores 47, behind V4 Pro but ahead of DeepSeek V3.2. This places it behind frontier models and at Claude Sonnet 4.6 (max) level intelligence. ➤ Leading agentic performance among open weights models: DeepSeek V4 Pro (Max) leads open weight models on agentic real-world work tasks, scoring 1554 on GDPval-AA. This places it ahead of Kimi K2.6 (1484), GLM-5.1 (1535), GLM-5 (1402), and MiniMax-M2.7 (1514). ➤ Gains in knowledge but an increase in hallucination rate: DeepSeek V4 Pro (Max) scores -10 on AA-Omniscience, an 11 point improvement over V3.2 (Reasoning, -21), driven primarily by higher accuracy. V4 Flash (Max) scores -23, broadly in line with V3.2. V4 Pro and V4 Flash both have a very high hallucination rate of 94% and 96% respectively meaning when they don’t know the answer they nearly always respond anyway. ➤ Flash materially behind Pro but well positioned for its size: DeepSeek V4 Flash (Max) scores 47 on the Artificial Analysis Intelligence Index, well below V4 Pro. However, at 284B parameters it is much smaller and is well positioned on the Intelligence vs Size frontier, sitting next to MiniMax-M2.7 ➤ Cheaper than frontier models but more expensive than other open weights models and a large increase over DeepSeek V3.2: DeepSeek V4 Pro costs $1,071 to run the Artificial Analysis Intelligence Index. This makes it more than 4x cheaper than Claude Opus 4.7 ($4,811), but it remains more expensive than several other open weights models, including Kimi K2.6 ($948), GLM-5.1 ($544), DeepSeek V3.2 ($71), and gpt-oss-120B ($67). DeepSeek V4 Flash is much cheaper at $113. ➤ High token usage: DeepSeek V4 Pro uses 190M output tokens to run the Artificial Analysis Intelligence Index, making it one of the most token-intensive models tested. DeepSeek V4 Flash is even higher at 240M output tokens. This high token usage helps explain why V4 Pro’s total cost remains relatively high versus other open weights models despite low per-token pricing. Key model details: ➤ Context window: 1M tokens, an 8x expansion on V3.2's 128K context window ➤ Modalities: Text input and output only, matching V3.2 ➤ Size: DeepSeek V4 Pro 1.6T total / 49B active; V4 Flash 284B total / 13B active ➤ License: MIT ➤ Availability: Available on DeepSeek's first-party API; we expect many third-party providers to host the models ➤ Pricing: DeepSeek V4 Pro $1.74 / $3.48 per 1M input/output tokens; V4 Flash $0.14 / $0.28 per 1M input/output tokens. Cache hit input token pricing is $0.145 for V4 Pro and $0.028 for V4 Flash per 1M tokens. V4 Pro is significantly more expensive than past DeepSeek R1 and V3 models

@smdcapital @ollama @Kimi_Moonshot well ollama is kinda messed up rn with its ttft . check ai-speedometer.oliveowl.xyz/?metric=f1000&…

FYI - using Kimi 2.6 via @ollama cloud is fucking garbage do NOT use ollama, it's way too slow and everything will break better to sign up directly with @Kimi_Moonshot

@robinebers ai-speedometer.oliveowl.xyz/?models=ollama…

has anyone tried limits on ollama cloud? especially interested in: - actual limits on Pro + Max - tok/s for the big models

@RhysSullivan I want to understand this better .this is like mcp porter thing wher it turns mcp into a cli but in broad like supporting all kinds of api? So like a cli for all the api as a client app for agent ?

objectively my favorite use case of executor.sh is i never have to configure DNS records in a UI again

@LLMJunky loving it

Limux Update 0.1.9! Added a bunch of requested features (thank you for all the issues & PRs). - Configurable keyboard shortcuts - Drag and drop tabs - Fullscreen support - Toggle Toolbar on/off - Desktop notifications for Codex - File drag & drop - AUR publishing Github 👇