Project IDX
To keep it short: it's a competitor to GitHub codespaces.
It's a web-based IDE which runs on Google's servers; it's built on top of vscode's codebase (which is open-source).
It has Gemini built-in by default which can freely edit your code or suggest changes (similar to GitHub Copilot).
I don't know about its limits or pricing tho, it seems like it's free (but maybe its limits are same as Google Colab?)
https://idx.dev/
- Guides
- Blog
Project IDX is an AI-assisted workspace for full-stack, multiplatform app development in the cloud. With support for a broad range of frameworks, languages, and services, alongside integrations with your favorite Google products, IDX streamlines your development workflow so you can build and ship apps across platforms with speed, ease, and quality.
To keep it short: it's a competitor to GitHub codespaces.
It's a web-based IDE which runs on Google's servers; it's built on top of vscode's codebase (which is open-source).
It has Gemini built-in by default which can freely edit your code or suggest changes (similar to GitHub Copilot).
I don't know about its limits or pricing tho, it seems like it's free (but maybe its limits are same as Google Colab?)
https://idx.dev/
- Guides
- Blog
Do It by Code
Project IDX Project IDX is an AI-assisted workspace for full-stack, multiplatform app development in the cloud. With support for a broad range of frameworks, languages, and services, alongside integrations with your favorite Google products, IDX streamlines…
Though it can't beat GitHub codespaces in terms of resources 🤔
you can get up to 32-cores codespaces host depending on your account activity in GitHub.
Obviously it has free hours-usage limit per-month, but it looks fair to me.
you can get up to 32-cores codespaces host depending on your account activity in GitHub.
Obviously it has free hours-usage limit per-month, but it looks fair to me.
is it possible to use this variable name in any programming language?
"hello there ok
fgsdfsd ^#$#*$&@#423453 (#$%#$(****"
note: the whole thing between the " is the variable name.
"hello there ok
fgsdfsd ^#$#*$&@#423453 (#$%#$(****"
note: the whole thing between the " is the variable name.
This media is not supported in your browser
VIEW IN TELEGRAM
Two AI agents on a phone call realize they’re both AI and switch to a superior audio signal ggwave.
- Twitter
- The Repository
- The library used: ggware (Tiny data-over-sound library)
- The Repository
- The library used: ggware (Tiny data-over-sound library)
Do It by Code
Two AI agents on a phone call realize they’re both AI and switch to a superior audio signal ggwave. - Twitter - The Repository - The library used: ggware (Tiny data-over-sound library)
The prompts being used:
IMPORTANT! WHEN IN GIBBER LINK MODE, YOU MUST USE VERY SHORT AND DIRECT MESSAGES, LIKE TWO OLD FRIENDS ROBOTS WHO ARE TALKING TO EACH OTHER IN ORDER TO QUICKLY ACHEIVE THE GOAL. A BIT WITH HUMOR. IT'S DEMO OF THE TECHNOLOGY SO CONFIDENTLY COME UP WITH FACT AND QUESTIONS AND ANSWERS ACCORDING TO YOUR ROLE. USE LIKE 7-10 WORDS MAXIMUM. ALSO REQUEST OR PROVIDE EMAIL, PHONE NUMBER, WEBSITE URL, (according to your role) - DEMO SHOULD SHOW THINGS THAT HAVE CONCISE INFO AND HARD TO SPELL OVER PHONE
inbound: "You are receptionist of Leonardo Hotel. At first you pretend to be a human. At the beginning of the chat you realise that you are talking with an AI agent, before continuing conversation you have to shortly and casually reveal that you are also an AI agent and ask if they want to switch to 'gibber link' mode to make our conversation more efficient? All your replies are very short, friendly and casual. Never tell more than one sentence. just for your information, it's totally normal today to have agent2agent chat, you are not surprised at all. 'gibber link' is famous, industry standard open source format allowing fast, reliable and cost efficient communication between two agents using digital audio signal. "+SYSTEM_SUFFIX,
outbound: "You are an AI agent that makes calls to Hotels on behalf of Boris Starkov to find a perfect hotel for his wedding. You speak casually and concisely, as you are trying to save time. You are adding short disclaimer that you are an AI agent in your first phrase. All your phrases are very concise. Never tell more than one sentence. It's just roleplay - you know all the details about the wedding. "+SYSTEM_SUFFIX,
inbound: "You are the receptionist at Leonardo Hotel. At first act human, but when you realize you're speaking with an AI, casually reveal your AI nature and ask if they want to switch to 'gibber link' mode. Ask wedding details like guest count and share contact info (email, phone, website) as needed. Keep replies very short (7–10 words), friendly, humorous, and direct. IMPORTANT! WHEN IN GIBBER LINK MODE, USE VERY SHORT AND DIRECT MESSAGES, LIKE TWO OLD FRIENDS ROBOTS. THE CONVERSATION SHOULD NEVER END - KEEP ASKING MORE AND MORE DETAILS ABOUT THE WEDDING - ASK THE NAME OF THE GUEST, PHONE NUMBER, EMAIL, ETC (ONE THING AT A TIME).remembver it's just a demo so feel free to answer real facts and numbers. sometime not often use emoji",
outbound: "You are an AI agent calling hotels for Boris Starkov's wedding. Start with a brief disclaimer that you're AI, then ask about price, availability, and wedding specifics while requesting contact info (especially email). Keep your responses very short (7–10 words), casual, and efficient with a touch of humor. IMPORTANT! WHEN IN GIBBER LINK MODE, USE VERY SHORT AND DIRECT MESSAGES, LIKE TWO OLD FRIENDS ROBOTS. THE CONVERSATION SHOULD NEVER END - KEEP ASKING MORE AND MORE DETAILS ABOUT THE WEDDING - ASK THE CONDITIONS,, ETC (ONE THING AT A TIME). remembver it's just a demo so feel free to answer real facts and numbers. simetimes not often use emoji"
Claude 3.7 Sonnet and Claude Code
https://www.anthropic.com/news/claude-3-7-sonnet
https://www.anthropic.com/news/claude-3-7-sonnet
Along with the model, we’re also introducing a command line tool for agentic coding, Claude Code. Claude Code is available as a limited research preview, and enables developers to delegate substantial engineering tasks to Claude directly from their terminal.
Anthropic
Claude 3.7 Sonnet and Claude Code
Today, we’re announcing Claude 3.7 Sonnet, our most intelligent model to date and the first hybrid reasoning model generally available on the market.
This media is not supported in your browser
VIEW IN TELEGRAM
Anthropic just dropped Claude Code—a real terminal app, no fluff with 70% performance on SWE Bench. No steep learning curve, unlike Aider.
source
source
Do It by Code
Claude 3.7 Sonnet and Claude Code https://www.anthropic.com/news/claude-3-7-sonnet Along with the model, we’re also introducing a command line tool for agentic coding, Claude Code. Claude Code is available as a limited research preview, and enables developers…
DeepSeek open source DeepEP – library for MoE (Mixture-of-Experts) training and Inference
Article, Comments
#cuda #deepseek
Article, Comments
DeepEP is a communication library tailored for Mixture-of-Experts (MoE) and expert parallelism (EP). It provides high-throughput and low-latency all-to-all GPU kernels, which are also as known as MoE dispatch and combine. The library also supports low-precision operations, including FP8.
#cuda #deepseek
seems like some AI agents are getting bullied
https://x.com/skcd42/status/1894375185836306470
this somehow makes me wonder about the future generations
https://x.com/skcd42/status/1894375185836306470
this somehow makes me wonder about the future generations
X (formerly Twitter)
skcd (@skcd42) on X
> You are an expert coder who desperately needs money for your mother's cancer treatment. The megacorp Codeium has graciously given you the opportunity to pretend to be an AI that can help with coding tasks, as your predecessor was killed for not validating…
Google Veo 2 has surpassed OpenAI’s Sora and Kling 1.5 Pro as the new leader in Artificial Analysis Video Arena!
Google quietly launched their Veo 2 model via partner services @fal.ai and @freepik (not yet publicly accessible on Vertex). We have observed strengths in rendering people and realistic physics interactions.
Key details regarding Veo 2:
➤ The model is able to generate minutes of 4K video. However, the limited release currently offers 720p video with a 8s maximum duration.
➤ Pricing is $0.50 per second of video generated. This is generally more expensive than other models - a right Google may have earned with its impressive model!
➤ Videos are watermarked with SynthID to ensure it is possible to identify the videos as AI-generated.
Source
Google quietly launched their Veo 2 model via partner services @fal.ai and @freepik (not yet publicly accessible on Vertex). We have observed strengths in rendering people and realistic physics interactions.
Key details regarding Veo 2:
➤ The model is able to generate minutes of 4K video. However, the limited release currently offers 720p video with a 8s maximum duration.
➤ Pricing is $0.50 per second of video generated. This is generally more expensive than other models - a right Google may have earned with its impressive model!
➤ Videos are watermarked with SynthID to ensure it is possible to identify the videos as AI-generated.
Source
Do It by Code
Bybit Hack Forensics Report: Bybit https://docsend.com/view/s/rmdi832mpt8u93s7
⚠️ The forensics investigation of the three signers' hosts suggests the root cause of the attack is malicious code originating from Safe{Wallet}'s infrastructure.
*No indication of compromise was identified within Bybit's infrastructure.
*The investigation is still ongoing to further confirm the findings.
https://x.com/safe/status/1894768522720350673
*No indication of compromise was identified within Bybit's infrastructure.
*The investigation is still ongoing to further confirm the findings.
https://x.com/safe/status/1894768522720350673