Gordon Beeming

Father • Husband • SSW Solution Architect (@SSW_TV)
Opinions are my own

[Boris Cherny @bcherny]

We wanted to do more for the people who’ve been with us the longest. So with Fable 5.2, the longer you’ve been subscribed, the more Fable resets you get.

[SSW / SSW TV @SSW_TV]

Does your next website really need React? 🤔

If you’re building pages, forms, and a few data tables, how much framework do you actually need?

Join Brook Jeynes at Brisbane Full Stack User Group to explore building lean with HTMX and Web Components.

📍 SSW Brisbane
📅 Wednesday 18 November

See the details and register:
https://t.co/zQtjS51c49

[Gordon Beeming @GordonBeeming]

@thsottiaux maybe we can finally update our mobile number now 😅... seems strange that with all this intelligence beneath us, we still can't keep our details up to date

[Mario Rodriguez @mariorod1]

Both Slack and Teams surfaces are GA and on a weekly release cadence. Keep your team in flow 🏎️

https://t.co/b6QkYHWaqp

[fouad @fouadmatin]

Today’s GPT-6 Cyber release is a meaningful step for defenders: stronger vulnerability research and better alignment. We’ve already been using GPT-6 Cyber alongside GPT-6 Astra with Daybreak to harden our own systems, finding weaknesses, validating their impact, and developing fixes.

Even after years @OpenAI, model capabilities continue to surprise me. One small example came from testing a prerelease version of GPT-6 Astra earlier this summer. We were examining tools used across our research infrastructure and one of our research infra leads, Michael Dalton, was looking into some low risk areas like a math task grader that used SymPy, a mathematics library, to check answers.

In an offline test, the submitted answer used characters that looked like ordinary letters to get past the grader’s checks. It caused the grader to run a shell command that printed “4242”, while still returning the expected result, 1/2. The grader marked the answer correct. A valid math answer had become a way to run code inside the grader - diagram below.

This is the kind of vulnerability that can be very hard for a human to find, even with a fuzzer. It takes connecting how input validation and evaluation interact, constructing an input that passes the checks but triggers unintended behavior, and recognizing the failure even when the final answer is correct. Models can reason across those pieces and help uncover classes of vulnerabilities that are difficult to spot when reviewing components in isolation.

That’s why it’s important for more defenders to use models with Daybreak to find and fix vulnerabilities in their own systems. Whether it’s a potentially internet-melting bug like PHP2Shell or a subtle but important issue like this grader bug, finding it before an attacker does gives defenders time to act.

Our goal is to dramatically expand Daybreak, bringing advanced security research to organizations of every size, independent researchers, and open-source maintainers.

We’re also expanding Daybreak Blue alpha access for GPT‑6 Astra to more organizations and individual security researchers - let us know if you’re interested:
https://t.co/0PpjMDDZJc

[Cloudflare Developers @CloudflareDev]

With the recent wave of vulnerability disclosures, it’s a good time to take a closer look at your own code.

Turn your coding agent into a team of security auditors with the open-source skill that seeded Cloudflare’s vulnerability discovery harness.

The 6 phase approach:
1. Map the codebase
2. Hunt for vulnerabilities
3. Challenge each candidate
4. Record the findings
5. Verify the findings
6. Report what’s confirmed, rejected, or still needs validation

Start your hunt here:
https://t.co/kL5PvcoAYY

[ClaudeDevs @ClaudeDevs]

Background subagents in Claude Code now use less of your usage limit.

A running subagent updates its status line every 30 seconds, and each update used to re-read its whole conversation. Now Haiku 5.5 writes it from short notes instead, so each update costs about 99% less.

[zcw @zwb44]

if anyone's confused, gpt plans used to be

5x - pro 100
20x - pro 200

then a month ago

5x - pro 100
10x - pro 200
25x - pro 500

now after today:

10x - pro 100
20x - pro 200
50x - pro 500

[Claude @claudeai]

A few upgrades to the Claude mobile apps this week:

On iPad and iPhone Duo: what Claude makes now opens beside the chat instead of over it, and goes full screen when you want a closer look.

[Tibo @thsottiaux]

Day 25/

We are doubling all usage limits for all Pro 100/200/500 tiers and Business Premium, effective today.

We heard your kind feedback and won’t be reducing usage limits for Pro 200, so your Work and Codex usage will stay the same. We’re also going to continue offering extended limits for dots for now, and usage of your dot will still continue to be separate from your default usage.

And we'll of course also keep shipping better models and other efficiency improvements that increase your effective usage over time.

[Gordon Beeming @GordonBeeming]

took a hot minute to😅

[GitHub Changelog @GHchangelog]

Commits now include a durable, authenticated pusher identity alongside author and committer info in the UI and API.
• New commit rule blocks pushes if committer metadata doesn’t match the pusher’s verified email

https://t.co/yL6LdGtq0l

[ClaudeDevs @ClaudeDevs]

We've added `ant apply` to the ant CLI.

Now you can declare Claude Managed Agent environments, agents, skills, memory stores, and deployments as files in your repository and keep the API's resources in sync with them using `ant apply`.

Docs: https://t.co/qQchmDjTmm

[ClaudeDevs @ClaudeDevs]

We're open-sourcing Claude Commerce Agents.

This is a blueprint for building shopping and merchant agents, with reference implementations across retail, travel, telecom, and entertainment.

[Gordon Beeming @GordonBeeming]

At least that's the video I thought I was clicking into 🫣

[Gordon Beeming @GordonBeeming]

Is it just me or did @BetterStackHQ fully steal the thumbnail design of @fireship_dev 😅

[valo @ValtteriValo]

codex six hours into a 15 minute task

[Noah @NoahKingJr]

Software developers in 2030 be like:

[ClaudeDevs @ClaudeDevs]

Claude Code can design now. The new /design skill (research preview) brings Claude Design's artboard workflow into the CLI and Desktop, built on artifacts.

Run /design to get editable artboards for your UI — pick one, tweak it, then have Claude implement it.

[ClaudeDevs @ClaudeDevs]

We’re extending the 50% increase to weekly Claude Code limits through August 31.

We hope to make this a permanent change to our plans, but strong demand for our models means that capacity may be tight over the coming weeks. We’ll keep you posted as things develop.

[ClaudeDevs @ClaudeDevs]

New in Claude Code: your sessions can now message each other.

Instead of having to re-explain yourself in another session, you can now tell Claude to do it. It sends a summary (not your history or files), and the other session picks it up mid-task.