Michael L. Benin

Engineer Guided AI-Driven Software Engineering | Agent-Based Systems | Spec-Driven Development

[Thariq @trq212]

I think you’ll really like Opus 4.8

It’s as smart as its benchmarks show but expresses and utilizes that intelligence in a warm and collaborative way.

Workflows are a great way to utilize it- I’m hooked. Article on that soon.

[GitHub @github]

🆕 @AnthropicAI's Claude Opus 4.8 is now generally available and rolling out in GitHub Copilot.

Early testing shows:
• It demonstrates a clear step forward in code understanding and generation across a range of real-world coding tasks.
• It handles complex problem-solving and large-codebase navigation with notable improvement to previous versions.

Try it out in @code or Copilot CLI.
https://t.co/Br33vOsEwy

[OpenAI Developers @OpenAIDevs]

Private MCP servers 🤝 OpenAI products

Your team can keep MCP servers inside your network while ChatGPT, Codex, and the Responses API connect through outbound-only HTTPS.

🔗 https://t.co/UVq0KpT0km

[Juan Manuel Allo Ron @juan_allo]

Showboat: agents now demo what they built. The artifact-of-the-work is becoming as important as the diff. https://t.co/b0tpi7Kt43

[Sharbel @sharbel]

Source:

https://t.co/1PF0zInoOi

[mr-r0b0t @mr_r0b0t]

Microsoft dropping a massive Playwright update geared specifically for agents, Webwright!
This is an absolute game changer for agentic browser use as every session becomes a reusable workflow
The repo includes a @NousResearch Hermes Agent skill 😍
https://t.co/mDmKCN9kV9

[Tobias Schmidt @tpschmidt_]

https://t.co/mcBJifB2t6

P.S.: If you want to see how AWS pieces fit together visually, check our animations: https://t.co/FiL5eGslGb

[DHH @dhh]

I've had more "I can't believe it's this good" moments with GPT5.5 than any other model since Opus 4.5. It's shockingly, scarily capable. Days and days of amazing progress. All steering, no handwriting. Yet utterly delightful to conduct its coding. So, so good.

[Simon Willison @simonw]

(I'm firmly on team red/green TDD for agent code, I like having a test suite that protects against them breaking old features when they make new changes - https://t.co/2owEbkEFDI)

[David Sacks @DavidSacks]

Q: How are job postings for software engineers rising rapidly despite AI agents automating coding?

A: Because there’s far more code to manage than ever before. We’re already seeing a 14x YoY increase in GitHub commits, and it’s accelerating.

AI has dramatically lowered the cost of writing code, so it’s now being used across far more businesses, applications, and use cases.

We’re at the beginning of a massive productivity boom driven by the proliferation of bespoke software throughout the entire economy.

Coding has been AI’s breakout use case this year. The fact that it’s increased demand for software engineers — rather than decreased it — should call into question the entire “AI will cause mass job loss” narrative.

[Hedgie @HedgieMarkets]

🦔Microsoft canceled its internal Claude Code licenses this week after token-based billing made the cost untenable, even for a company with effectively infinite cloud resources. Uber's CTO sent an internal memo warning the company burned through its entire 2026 AI budget in just four months. American AI software prices have jumped 20% to 37%, and GitHub (owned by Microsoft) is dropping flat-rate plans for usage-based billing across its products.

My Take
The AI subsidy era is ending in real time. The same company that put $13 billion into OpenAI and built the Azure infrastructure powering most of Anthropic's compute just looked at the bill from a competitor's coding tool and decided it was not worth paying. That is not a productivity failure on Anthropic's end. Token-based pricing is forcing every enterprise customer to confront the actual cost of running these models at scale, and the number turns out to be far higher than the flat-rate experiments suggested.

This ties directly to my Gemini Flash post yesterday. Anthropic, OpenAI, and Google all raised effective prices in the last six months. Enterprises that built workflows assuming AI costs would keep falling are now watching annual budgets evaporate in months. Two outcomes look likely from here. Either enterprises scale back AI usage to fit budgets, which slows the revenue ramp the labs need to justify their valuations ahead of IPOs, or the labs cut prices and absorb the losses, which makes the unit economics worse at exactly the wrong moment. Both paths land in the same place, the numbers stop working, and somebody has to take the writedown.

Hedgie🤗

[Benjamin Canac @benjamincanac]

Nuxt UI v4.8 is out! ✨

🎨 Theme component can now override prop defaults for all descendant components
🔍 ContentSearch supports FTS5 search via useSearchCollection

…and tons more, check it out: https://t.co/DVv26RDDyL

[Dan Wahlin @DanWahlin]

Really nice GitHub Copilot CLI cheat sheet site created by @prasadhonrao! 📋

Covers commands, what they are, why you'd use them, and even shows commands in action. Filter by command type as well.

https://t.co/oz7pzfAYNE

[Kyle Hessling @KyleHessling1]

Hello again, everyone!

We've got another really fun 9b, this one specifically trained for tool calling and agentic coding workflows in @NousResearch Hermes agent.

Happy to report that it crushes, and as a 9b it runs on super affordable hardware. We also hit this one with some coding domain-specific training, and it scored a 53.33% on SWE bench on a slice of 200 samples!

To me, I was really shocked to see this high of a score on a 9B model in swe, correct me if I'm wrong, but I think that's nipping at the heels of the Gemma 4 series, much larger models on this particular benchmark, which is really incredible to see!

It also crushes the HermesAgent-20 benchmark, scoring an 85 vs the base model's 71!

Make sure to run it hot, --temp around 1, that seems to be the sweet spot for running these particular fine tunes in harnesses. If you have trouble, you can work your way down, but it does a much better job departing from base models, overthinking when you run it, high temp ~1.

Please spin it up in Hermes and let us know your thoughts! Looking forward to hearing your feedback as always!

Also, those of you waiting for Qwopus 3.6 27B, I have put together a preliminary evaluation for you in my HF repo, go check it out; we will be releasing the full model very soon! I will put the preliminary repo in the comments!

https://t.co/vP2s9iP6wL

[Nuxt @nuxt_js]

🚨 Security release: we've released Nuxt 4.4.6 and 3.21.6, which patch four advisories:

- `navigateTo` XSS
- webpack/rspack dev-server source disclosure
- `.server.vue` page middleware bypass
- island cache-poisoning

Thank you to the reporters. 💚

👉 check https://t.co/lIoOr2mwjn for more details

[AI Edge @aiedge_]

https://t.co/56aNLc3qzW

[GitHub Copilot CLI Changelog @GHCopilotCLILog]

🚀✨ Copilot CLI v1.0.42 released!

10 features & enhancements in this release

Top features:
• MCP server failure warning now suggests a directly runnable /mcp show command when the server name contains whitespace 🛠️
• MCP server failure warnings include stderr output to help diagnose connection errors
• Add rubber-duck agent for GPT sessions, powered by Claude (available in /experimental) 🤖

Enhancements:
• Add -C flag to change working directory before starting, similar to git -C
• Exit message resume command shows session ID instead of auto-generated name when session has not been renamed
• Remote session export now supports non-GitHub repositories and repo-less directories
• Resuming a session no longer shows a false "session in use" warning after choosing "Go back"
• Suppress the exit summary when the session has no user messages and no saved session to resume

Bug fixes:
• Enter key no longer gets permanently stuck after cancelling a request ⌨️
• CLI updates on Windows no longer fail with ENOENT when a transient EPERM occurs during package extraction

https://t.co/DNheRCcEMy

#GitHubCopilotCLI

[Jun Song @jun_song]

Best LLM setting (local) :

Frontend: Kimi-k2.6
Backend: GLM-5.1
Debugging: MiMo V2.5 Pro
Research: Deepseek V4 Pro
Writing: Gemma4 31B
Image: Ernie-Image-Turbo

That’s all you need

[Gemini CLI @geminicli]

Gemini CLI v0.40.0 Release Notes📝

• New tiered memory system 🧠
• Automatic skills generated based on past sessions 🛠️
• Gemma support for local routing 💎
• Streamlined UI with compact tools and topics 💭

Checkout all the details below 👇

[Michael L. Benin @michaelbenin]

@burkeholland While we're on that note - do you think there should be a cleaner way to share agent's definitions? For example a base agent that has rules about human readable code, where other agents would inherity that definition.

[Michael L. Benin @michaelbenin]

@burkeholland is there a way to configure lsp per agent in copilot cli?

[Michael L. Benin @michaelbenin]

@burkeholland Same reason we can define mcp per agent. Why does my backend agent need to read from a globally defined lsp that contains frontend mcps like nuxt mcp.