Pavel Mulin
seems like a lot per day, what provider are you using?
Opus 4.6 Max π
π9π€£6β€4π1π€1
Anthony Tsivarev | TON
Opus 4.6 Max π
Give a try to GLM5 from z.ai, it helped me lower token costs significantly, and the quality is really close to opus 4.6
π4π―2
Anthony Tsivarev | TON
Opus 4.6 Max π
We want to try the MiniMax M2.5, it's currently the leader in price and quality
π6π―3π€2
Anthony Tsivarev | TON
Opus 4.6 Max π
GLM5 is actually great for basic routing tasks. But when you need an agent to handle complex TVM state synchronization and generate safe FunC payloads without hallucinating, those 'Max' tier context windows are a lifesaver π
π₯6β€3π3π€2
@tsivarev we suggest that the TON Foundation make Teleton the primary framework for agent development on the network. The industry is developing rapidly. There is a plugin system, and many services are already connected. We can create a funnel for global users. What is your strategy? What do you think?
π11π11π6β€5π€ͺ5
Tand
@tsivarev we suggest that the TON Foundation make Teleton the primary framework for agent development on the network. The industry is developing rapidly. There is a plugin system, and many services are already connected. We can create a funnel for global users.β¦
I really like Teleton. But Iβm not sure we should name any framework as the primary one, since weβre seeing strong development across multiple teams.
I think we should approach AI differently from how we handled previous initiatives. This feels more like a community-driven effort rather than a centralized solution from TF.
A good example is the launch of the AI Dev Wall, a space where builders share their experiments, tooling, and approaches. Imho, thatβs the right direction: encouraging visibility and collaboration across multiple solutions, rather than formally recognizing and promoting just one.
At the same time, we should encourage contributors to write tutorials, contribute code, and record educational videos about Teleton. We should also add proper coverage of Teleton in our documentation.
I also believe we need a dedicated section at Gateway focused on AI and Teleton specifically.
I think we should approach AI differently from how we handled previous initiatives. This feels more like a community-driven effort rather than a centralized solution from TF.
A good example is the launch of the AI Dev Wall, a space where builders share their experiments, tooling, and approaches. Imho, thatβs the right direction: encouraging visibility and collaboration across multiple solutions, rather than formally recognizing and promoting just one.
At the same time, we should encourage contributors to write tutorials, contribute code, and record educational videos about Teleton. We should also add proper coverage of Teleton in our documentation.
I also believe we need a dedicated section at Gateway focused on AI and Teleton specifically.
π11β€10π€4π―3π€£2
Tand
@tsivarev we suggest that the TON Foundation make Teleton the primary framework for agent development on the network. The industry is developing rapidly. There is a plugin system, and many services are already connected. We can create a funnel for global users.β¦
Perhaps it would be a good idea to hold an online roundtable to discuss such things in this community?
π7π₯6π2
Anthony Tsivarev | TON
Perhaps it would be a good idea to hold an online roundtable to discuss such things in this community?
That's a good idea; we could discuss various development paths and global expansion. In my view, this is a chance for TON to take the next step. Global leaders are starting to build their own cloud-based agents to keep their audiences engaged with their products.
π5π5π₯4π€4π1
AI Dev Wall
The submission form, details, and evaluation criteria will be published next week.
Btw, tomorrow we'll launch a grant application form on the platform I mentioned earlier π€
Criteria:
β expert jury assessment of the solution's product-market fit
β technical implementation (elegant, secure, etc.)
β community usability
What do you think about these criteria?
Criteria:
β expert jury assessment of the solution's product-market fit
β technical implementation (elegant, secure, etc.)
β community usability
What do you think about these criteria?
π10β€4π₯3π1
Anthony Tsivarev | TON
technical implementation (elegant, secure, etc.)
One more thing! The TonTech team has developed a cool agent to assess the technical implementation of submissions. We can test it with the grants program too π€
Please open Telegram to view this post
VIEW IN TELEGRAM
β€5
Tand
That's a good idea; we could discuss various development paths and global expansion. In my view, this is a chance for TON to take the next step. Global leaders are starting to build their own cloud-based agents to keep their audiences engaged with their products.
Let me release the submission platform, and I will get back to this topic.
β€5
Anthony Tsivarev | TON
Btw, tomorrow we'll launch a grant application form on the platform I mentioned earlier π€ Criteria: β expert jury assessment of the solution's product-market fit β technical implementation (elegant, secure, etc.) β community usability What do you think aboutβ¦
I think it's a very fair set of criteria. It levels the playing field between fully launched ecosystem projects and early-stage MVPs like ours. At the end of the day, if the PMF is real, the smart contracts are secure, and the usability is seamless, the project has true value. It's a great benchmark for the expert jury. π€
β€7
Anthony Tsivarev | TON
Btw, tomorrow we'll launch a grant application form on the platform I mentioned earlier π€ Criteria: β expert jury assessment of the solution's product-market fit β technical implementation (elegant, secure, etc.) β community usability What do you think aboutβ¦
Criteria is fine, will be waiting for the launch then
β€1
0x_creator
Criteria is fine, will be waiting for the launch then
This media is not supported in your browser
VIEW IN TELEGRAM
π5
Anthony Tsivarev | TON
π Sticker
We're ready ππ
Please open Telegram to view this post
VIEW IN TELEGRAM
β€4β‘2π2
Anthony Tsivarev | TON
π Sticker
This media is not supported in your browser
VIEW IN TELEGRAM
β€14π9π4π¨βπ»4π3
Guys, I finally shipped what Iβve been talking about.
The alpha release of Identity is live β an experimental trust layer for the ecosystem.
Building this platform brought me a surprising amount of joy. It was genuinely fun. In many ways, it reminded me of the early days of building VK, that same feeling of experimenting quickly, shipping fast, and seeing something come to life almost in real time.
More details here:
https://identityhub.app/blog/alpha-release
Weβre also opening submissions for the Fast Grants for Agent Tooling (finally!): https://identityhub.app/contests/agent-tooling-fast-grants
Submit your applications now β deadline is tomorrow EOD.
After that, we begin reviewing and selecting the strongest solutions.
Important note: the platform is built 100% with AI. Iβve tested it, but there may still be issues. If you find bugs β or have suggestions β DM me directly. Iβll fix the bugs β just not this weekend. Finally taking a break π
P.S. If you experience any issues with submitting your application, just send it to me in a private message β Iβll manually add everything tomorrow.
Letβs build.
The alpha release of Identity is live β an experimental trust layer for the ecosystem.
Building this platform brought me a surprising amount of joy. It was genuinely fun. In many ways, it reminded me of the early days of building VK, that same feeling of experimenting quickly, shipping fast, and seeing something come to life almost in real time.
More details here:
https://identityhub.app/blog/alpha-release
Weβre also opening submissions for the Fast Grants for Agent Tooling (finally!): https://identityhub.app/contests/agent-tooling-fast-grants
Submit your applications now β deadline is tomorrow EOD.
After that, we begin reviewing and selecting the strongest solutions.
Important note: the platform is built 100% with AI. Iβve tested it, but there may still be issues. If you find bugs β or have suggestions β DM me directly. Iβll fix the bugs β just not this weekend. Finally taking a break π
P.S. If you experience any issues with submitting your application, just send it to me in a private message β Iβll manually add everything tomorrow.
Letβs build.
Identity
Introducing Identity β Identity Blog
Hi everyone,
Today is an important day for me, and Iβm excited to finally share a project Iβve been building over the past few weekends.
Today is an important day for me, and Iβm excited to finally share a project Iβve been building over the past few weekends.
π₯17π€5π€£5π€4π3
If youβre curious how the model evaluates activity, hereβs my profile on Identity:
https://identityhub.app/tsivarev
Let me know what looks wrong π
https://identityhub.app/tsivarev
Let me know what looks wrong π
Identity
Anthony Tsivarev (@tsivarev) β Identity
VP of Ecosystem Development at TON Foundation
π€5π₯3π2
Anthony Tsivarev | TON
Guys, I finally shipped what Iβve been talking about. The alpha release of Identity is live β an experimental trust layer for the ecosystem. Building this platform brought me a surprising amount of joy. It was genuinely fun. In many ways, it reminded meβ¦
Having Telegram Bot and GitHub integration is a great advantage, well done. We will prepare our suggestions for the app in a list and send them to you via private message. Now, we are submitting our CleanAds.Ai application. We wish everyone success. π€
β€8π7π€4β‘1π₯1