AI Coding Community

More
(14) Povilas Korop | Laravel Courses Creator & Youtuber on X: "Today I was surprised by MiMo-v2.5-Pro AI coding model. It suddenly auto-switched into Plan mode (in Opencode), so when I got back to computer in 10 minutes, planning to review the FINISHED task, it was like "here's the plan, should I go ahead?" For a pretty trivial task. And https://t.co/t0sWvmLv2a" / X
(14) Povilas Korop | Laravel Courses Creator & Youtuber on X: "Today I was surprised by MiMo-v2.5-Pro AI coding model. It suddenly auto-switched into Plan mode (in Opencode), so when I got back to computer in 10 minutes, planning to review the FINISHED task, it was like "here's the plan, should I go ahead?" For a pretty trivial task. And https://t.co/t0sWvmLv2a" / X
Povilas on X: "MiMo-v2.5-Pro in OpenCode is often auto-switching into Plan mode"
·x.com·
(14) Povilas Korop | Laravel Courses Creator & Youtuber on X: "Today I was surprised by MiMo-v2.5-Pro AI coding model. It suddenly auto-switched into Plan mode (in Opencode), so when I got back to computer in 10 minutes, planning to review the FINISHED task, it was like "here's the plan, should I go ahead?" For a pretty trivial task. And https://t.co/t0sWvmLv2a" / X
(21) Cursor on X: "Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we’re doubling the included usage of the model. https://t.co/N87ojcXlOC" / X
(21) Cursor on X: "Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we’re doubling the included usage of the model. https://t.co/N87ojcXlOC" / X
Cursor on X: "Introducing Composer 2.5, our most powerful model yet."
·x.com·
(21) Cursor on X: "Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we’re doubling the included usage of the model. https://t.co/N87ojcXlOC" / X
(13) ClaudeDevs on X: "What are best practices for running Claude Code at scale? New blog post on what we've learned from teams running it across multi-million-line monorepos, decades-old legacy systems, and distributed microservices: https://t.co/rJUYlIUiTT" / X
(13) ClaudeDevs on X: "What are best practices for running Claude Code at scale? New blog post on what we've learned from teams running it across multi-million-line monorepos, decades-old legacy systems, and distributed microservices: https://t.co/rJUYlIUiTT" / X
ClaudeDevs on X: "What are best practices for running Claude Code at scale? New blog post on what we've learned from teams running it across multi-million-line monorepos"
·x.com·
(13) ClaudeDevs on X: "What are best practices for running Claude Code at scale? New blog post on what we've learned from teams running it across multi-million-line monorepos, decades-old legacy systems, and distributed microservices: https://t.co/rJUYlIUiTT" / X
(12) Daniel San on X: "Claude Code 2.1.139 added /goal You set a completion condition and Claude keeps working across turns until it's met Works in interactive, -p, and Remote Control 👏 https://t.co/ETyGjplaOC" / X
(12) Daniel San on X: "Claude Code 2.1.139 added /goal You set a completion condition and Claude keeps working across turns until it's met Works in interactive, -p, and Remote Control 👏 https://t.co/ETyGjplaOC" / X
Daniel on X: "Claude Code 2.1.139 added /goal"
·x.com·
(12) Daniel San on X: "Claude Code 2.1.139 added /goal You set a completion condition and Claude keeps working across turns until it's met Works in interactive, -p, and Remote Control 👏 https://t.co/ETyGjplaOC" / X
(21) Mateusz Mirkowski on X: "🇨🇳After testing Chinese models over the last few weeks, my coding ranking currently looks like this: 1. Kimi K2.6 2. GLM-5.1 3. MiMo V2.5 Pro 4. MiniMax 2.7 5. DeepSeek V4 Pro 👉But each of them has its own superpowers. Frontend/Design: K2.6 Backend: K2.6 / GLM-5.1 Code" / X
(21) Mateusz Mirkowski on X: "🇨🇳After testing Chinese models over the last few weeks, my coding ranking currently looks like this: 1. Kimi K2.6 2. GLM-5.1 3. MiMo V2.5 Pro 4. MiniMax 2.7 5. DeepSeek V4 Pro 👉But each of them has its own superpowers. Frontend/Design: K2.6 Backend: K2.6 / GLM-5.1 Code" / X
Mateusz on X: "After testing Chinese models over the last few weeks, my coding ranking currently looks like this."
·x.com·
(21) Mateusz Mirkowski on X: "🇨🇳After testing Chinese models over the last few weeks, my coding ranking currently looks like this: 1. Kimi K2.6 2. GLM-5.1 3. MiMo V2.5 Pro 4. MiniMax 2.7 5. DeepSeek V4 Pro 👉But each of them has its own superpowers. Frontend/Design: K2.6 Backend: K2.6 / GLM-5.1 Code" / X
(16) CJ Zafir on X: "Codex 5.5 hack: "Are you 100% confident in this strategy? If not, find all possible loopholes, suggest proper fixes and run this loop until you are factually 100% confident in the new startegy" This works like charm. It makes Codex 5.5 high perform even better than codex 5.5" / X
(16) CJ Zafir on X: "Codex 5.5 hack: "Are you 100% confident in this strategy? If not, find all possible loopholes, suggest proper fixes and run this loop until you are factually 100% confident in the new startegy" This works like charm. It makes Codex 5.5 high perform even better than codex 5.5" / X
CJ on X: "Codex 5.5 hack: Are you 100% confident in this strategy?"
·x.com·
(16) CJ Zafir on X: "Codex 5.5 hack: "Are you 100% confident in this strategy? If not, find all possible loopholes, suggest proper fixes and run this loop until you are factually 100% confident in the new startegy" This works like charm. It makes Codex 5.5 high perform even better than codex 5.5" / X
(20) Vaibhav (VB) Srivastav on X: "Team shipped a Codex Security plugin with 5 AppSec workflows: > Security Scan Scans PRs, commits, branches, patches, folders, or full repos. Runs the full pipeline end-to-end > Threat Model Maps the repo: assets, trust boundaries, attacker inputs, invariants, and failure https://t.co/jUAB571N2I" / X
(20) Vaibhav (VB) Srivastav on X: "Team shipped a Codex Security plugin with 5 AppSec workflows: > Security Scan Scans PRs, commits, branches, patches, folders, or full repos. Runs the full pipeline end-to-end > Threat Model Maps the repo: assets, trust boundaries, attacker inputs, invariants, and failure https://t.co/jUAB571N2I" / X
Team shipped a Codex Security plugin with 5 AppSec workflows.
·x.com·
(20) Vaibhav (VB) Srivastav on X: "Team shipped a Codex Security plugin with 5 AppSec workflows: > Security Scan Scans PRs, commits, branches, patches, folders, or full repos. Runs the full pipeline end-to-end > Threat Model Maps the repo: assets, trust boundaries, attacker inputs, invariants, and failure https://t.co/jUAB571N2I" / X
(20) Ronin on X: "I cut my Claude Code bill ~80% with one move: I actually read the docs.. > /clear when context hits 50% > /context to see what's bloating it > prompt caching (free, just enable it) > CLAUDE.md scoped per-task, not global > subagents for anything that returns >2k tokens No Rust https://t.co/7m4mkGHQiN" / X
(20) Ronin on X: "I cut my Claude Code bill ~80% with one move: I actually read the docs.. > /clear when context hits 50% > /context to see what's bloating it > prompt caching (free, just enable it) > CLAUDE.md scoped per-task, not global > subagents for anything that returns >2k tokens No Rust https://t.co/7m4mkGHQiN" / X
Ronin on X: I cut my Claude Code bill ~80% with one move: I actually read the docs
·x.com·
(20) Ronin on X: "I cut my Claude Code bill ~80% with one move: I actually read the docs.. > /clear when context hits 50% > /context to see what's bloating it > prompt caching (free, just enable it) > CLAUDE.md scoped per-task, not global > subagents for anything that returns >2k tokens No Rust https://t.co/7m4mkGHQiN" / X