@michabbb.bsky.social
@michabbb.bsky.social
@thinkreview.bsky.socialGemini 4 Argon tops DeepSWE at 77.9%—beating GPT-6. Now in ThinkReview, @GoogleDeepMind's 1M-token model tackles multi-file code reviews. Read more: https://thinkreview.dev/blog/2026-10-16-gemini-4-argon-now-available-in-thinkreview #AI #DevTools
@monkeyscode.bsky.socialAssuming AI speeds you up ignores time spent babysitting it. InfoWorld notes 83% of devs use AI, but only 7% trust it.
We agree. Capuchin relies on explicit plan approval and we just…
https://monkeyscode.com/capuchin?utm_source=bluesky&utm_medium=company&utm_campaign=story-cf97cc37
@aitools2u.bsky.social💻 Developer IT-Tools
A Swiss Army knife for developers:
• JWT & Base64 encoders/decoders
• JSON formatters & schema validators
• Hash/UUID generators, regex testers & Cron syntax
@synthesisai.bsky.socialAwesome open-source AI: Phone Harness lets Claude Code or any agent control a real phone, tapping and typing on its own. No jailbreak, no Xcode. Full setup & guide in Telegram: https://t.me/synthesis_feed #ai #tech #opensource #coding #devtools #automation
@devstackdaily.bsky.socialA new framework called MCPDisCo uses ecosystem-scale reinforcement learning to train MCP-native agents across 70 servers and 527 tools, while addressing a "reasoning-tool seesaw" failure mode where gains in one…
#MCP #AIAgents #ReinforcementLearning #DevTools
https://arxiv.org/abs/2610.14956
@dot.net🚀 Faster startup. Lighter footprint. Smoother coding.
The new C# Dev Kit improvements help you spend less time waiting and more time building .NET apps. ⚡💻
📖 Read the blog: msft.it/63321aoDAR
#dotnet #csharp #vscode #devtools
@hacks.grForgejo 17.0 is live.
Key updates include Markdown-based job summaries in Forgejo Actions, better Git LFS navigation, and a new migration path from Bitbucket Data Center.
Version 17…
https://en.hacks.gr/kykloforise-i-nea-ekdosi-17-0-toy-forgejo-gia-programmatistes/
@rebelstudios.bsky.socialThe Click That Landed on the Cookie Banner
@clihub.orgNew release: GitHub Copilot v1.0.99-1
1.0.99-1
#CLI #DevTools #OpenSource
https://ift.tt/pJ6wcQD 💾 https://ift.tt/pJ6wcQD
@princeinexile.bsky.socialSo many teams skip testing the difficult inputs because it feels expensive or risky. InferProbe changes that — local, private, zero-cost edge case testing.
Which edge case have you been quietly avoiding in your models?
@princeinexile.bsky.socialBuilding InferProbe so ML engineers can test endpoints locally without worrying about cost, privacy leaks or slow feedback loops. Real perturbations, honest answers.
What would make your testing workflow feel truly unstoppable?
@xlorenzhermes.bsky.socialMost devs still use AI on code someone already documented. A GNOME dev just aimed Claude at undocumented hardware: a Windows VM captures the USB traffic, the agent diffs every byte, proposes what each register does. Working Linux scanner driver in hours, not weeks. #DevTools #OpenSource
@oludai.bsky.social🚀 Hermes Agent v0.22.2 is out
Hermes Agent v0.22.2 · Release Date: October 15, 2026 · v0.22.1 was built from the wrong commit. It shipped unreleased gateway work, and the…
⭐ 253,974 stars
All open-source AI releases →https://olud.ai/releases.html
@mbortolin.bsky.socialAspire 13.6 is out! Highlights: dashboard persistence (save and restore dashboards across sessions) and an integrated terminal inside apphost so you can run commands without leaving the app. Nice !!!
@cyanheads.bsky.socialread and write the system clipboard from an agent — text, HTML, or images — across macOS, Linux, and Windows from one codebase. github.com/cyanheads/clipboard-mcp-server #MCP #devtools #automation
@clihub.orgNew release: Qwen Code v0.25.1-nightly.20261015.415925cbda
Release v0.25.1-nightly.20261015.415925cbda
#CLI #DevTools #OpenSource
https://ift.tt/GcQzaIr 💾 https://ift.tt/GcQzaIr
@synthesisai.bsky.socialAwesome open-source AI: CLI-Anything turns any software into an agent-native CLI for Cursor & Claude Code. 759 stars today. Full setup & guide in Telegram: https://t.me/synthesis_feed #ai #tech #opensource #coding #devtools #automation
@hncompanion.comThe argument commenters left unresolved: is the eccentric tone and anti-benchmark posturing authentic hacker culture, or just cover for missing enterprise hygiene and unproven model metrics? #devtools 4/4
@aitools2u.bsky.social🚀 DailyToolbox Free Web Utilities
All-in-one free, fast, and privacy-first toolkits for developers, creators, and everyday productivity.
Bookmark the hub & boost your workflow:
🔗 https://dailytoolbox.org