Srinivas

I am a coder but learning marketting and documenting my findings

[Srinivas @SrinivasValekar]

Here is my first community contribution - Nft Staking - https://t.co/OENbb9r78n

Inspired by @gajeshnaik, @therealchaseeb and @SuperteamDAO, I will now start to add example @solana programs and help community.

[Srinivas @SrinivasValekar]

@HarshalsinghCN This is exactly what I was looking for! Thank you.

[Srinivas @SrinivasValekar]

@Saiero183539 @0xSero Their TOS strictly prohibits using their models anywhere outside their ecosystem

[Srinivas @SrinivasValekar]

@0xSero Yes absolutely agree, but it had some ui issues, switched back to using codex

[Srinivas @SrinivasValekar]

@omarsar0 I thought that this paper was related is to this - https://t.co/eurM7bdV0l

[Srinivas @SrinivasValekar]

@TheDeBattyGroup @mitsuhiko Use vibe proxy, you can use your sub everywhere in the system.

[Srinivas @SrinivasValekar]

@hsu_steve @grok - does this mean that I have access to Claude latest models with glm subscription?

[Srinivas @SrinivasValekar]

@ECLresearch @omarsar0 According to what I read, this repo threatened existing projects and higher management

[Srinivas @SrinivasValekar]

@orcus108 Need to evaluate with deepswe . Then we would have real results.

[Srinivas @SrinivasValekar]

@jietang This is a good model, I was surprised when it handled fixing bugs with the large codebase correctly. This is a bug fixer model for me :)

[Srinivas @SrinivasValekar]

@aakrit Would love to contribute if you open source your codebases :)

[Srinivas @SrinivasValekar]

@matei_zaharia Now my Hermes agent will have single knowledge base of all my projects! Trying this out

[Srinivas @SrinivasValekar]

@skirano Even I was thinking the same, but I would atleast need $10k to get started with.

[Srinivas @SrinivasValekar]

@htwtech_RPC Even I am amazed at how good glm is.

[Srinivas @SrinivasValekar]

This is the best open source model so far, compared to other open source models. On par with gpt 5.5 high.

1. Minimax - good all rounder, best for outer harness
2. Kimi 2.7 code - good reviewer
3. Mimo 2.5 Pro - good at deep analysis.
4. Deepseek V4 pro - this is okay, good at testing. Good for long horizon tasks.
5. Glm 5.2 - very good for planning,implementation and reviewing.

[Z.ai @Zai_org]

Intelligence should be open, accessible, and ready to build with, empowering every developer, everywhere.

GLM-5.2 is now available to all GLM Coding Plan users, including Lite, Pro, Max, and Team plans.
https://t.co/AedZACyzej

As our new flagship model, GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks.

API and Chatbot services will launch next week. The model will also be officially open-sourced next week under the MIT License.

The future of AI is open, and it belongs to the people.

[Srinivas @SrinivasValekar]

@Zai_org I tried this out, I can say that this model is on par with gpt 5.5 high. Thanks @Zai_org 👍

[Srinivas @SrinivasValekar]

@htwtech_RPC Yes, absolutely, I already like kimi 2.6 which is very good orchestrator in Hermes setup currently.

[Srinivas @SrinivasValekar]

This is best at reviewing, caught a few gaps that gpt 5.5 xhigh completely missed.

[Kimi.ai @Kimi_Moonshot]

🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!

🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite.
🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.

⚡️ 6x High-Speed Mode coming soon!
🔌 Available today via Kimi API and Kimi Code.

🔗 Kimi Code: https://t.co/uvoSJKyGCY
🔗 API: https://t.co/EOZkbOwCN4

[Srinivas @SrinivasValekar]

@LonnyLot @Kimi_Moonshot I would definitely need a few dgx spark or a6000 to run this locally. Very costly. Better subscribe for the plan.

Have been using kimi2.7 code , best at reviewing that gpt 5.5 completely missed.

[Srinivas @SrinivasValekar]

@levelsio I couldn't. But it's unsettling that I freedom of replying to anyone has been taken

[Srinivas @SrinivasValekar]

@noplanBworld They have to!

[Srinivas @SrinivasValekar]

Apple partnering with google is a good move in 2026