Creator of https://nitter.cf/t.co/RPlEpqMeP8, Rapid Reviews for Shopify https://nitter.cf/t.co/4Uo0CtB6yV, Image Sitemap for Shopify https://nitter.cf/t.co/KtEbAggRbD
Joined February 2009
- Tweets1.7K
- Following269
- Followers3.3K
- Likes1.7K
Pinned Tweet
I built a knowledge/chat agent that actually sees inside your Shopify app.
It knows every screen, every button, every text block, and every link — and can deep-link users directly into the right page of your live app.
It’s called Zero Docs.
zerodocs.io
▻ Drop the agent directly into your live app
▻ Use our Chrome extension to capture your authenticated app screens
▻ It answers with real layout intelligence + deep links
▻ Reduce your support requests by 80%
▻ One click and it writes your docs too
Deploy it in 10 minutes. Free to try. Plans start at $10/mo.
First 50 Shopify apps get 4 free months of Bootstrap or Starter plans — just DM me or use code SHOPIFY4 at checkout.
I'd love feedback from other Shopify devs — especially if you’ve tried other AI "chat" agents before.
Son of a Twinkie
BREAKING: Binance has been hacked with wallets across the Ethereum, Bitcoin, and TRON networks seeing outflows of -$5.7 billion.
The hack includes $1.45 billion worth of Bitcoin and $875 million worth of ETH.
If confirmed, this would mark the biggest hack in crypto history.
We expect more information shortly.
It seems to be the case that LLMs are much better at deconstructing than creating
The big security breaches and library patches will continue indefinitely
This means more work for software engineers for a decade, mentorship, training, study
Our short term productivity spikes that we're seeing from the LLMs should be weighted against increased future complexity
We'll have to budget 5x more time and effort for security moving forward
William Belk retweeted
Full details of a remotely exploitable vulnerability in the core engine of *all* PHP versions will be released tomorrow, October 21st. If your organization has internet facing PHP applications then you need to be ready to patch the minute the update is released or *strongly* consider taking the application offline until you can:
php.net/index.php#2026-10-20…
🚨 PHP warns of two critical vulnerabilities as emergency patches arrive tomorrow
The PHP security team will release updates on October 21 at 14:00 UTC for two vulnerabilities, each rated 9.2 under CVSS v4.0.
⠀
Security researchers identified the flaws as CVE-2026-109618 and CVE-2026-109619 and described them as remote code execution vulnerabilities reportedly affecting PHP versions 5 through 8.
PHP has not yet confirmed the affected versions, exploitation requirements or fixed releases.
⠀
The vulnerabilities were reportedly leaked before their planned disclosure. Researchers said they have not observed active exploitation, while PHP warned it may release the patches early if technical details become public or exploitation is detected.
⠀
Administrators should identify PHP installations now and prepare to apply the updates as soon as they become available.
LLMs do compress time and expand scope, but the tradeoff between development speed and quality is still very acute
The scope expansion available with LLMs requires more tooling, automation, and planning
Human strategic intelligence is still the singular ingredient that frames success and innovation
We're definitely net improved with LLMs, but people are out here reckless and feeding unrealistic expectations that hurt quality and project success
just updated my Pi / oh-my-pi agent behavior control plugin
- improved agent review process
- updated for latest OMP version
github.com/wbelk/pi-behavior…
Human strategic intelligence is still the value differentiator
A plague of LLM stenography is sweeping the corporate and agency worlds
Think more, write less, say less
William Belk retweeted
hunk v0.24.0 is out - with improvements from 20+ contributors 🔥
including:
- open any file or directory with `hunk open`
- merge conflicts now render correctly
- configurable auto layout
- CLI tab autocomplete, scroll_off, and much more
🎨 hunk v0.23.0 is out:
- your terminal colours right in hunk (thanks @dhh)
- review GitHub PRs in hunk via `hunk gh pr`
- proper text search via `/` (thanks @elucid_ont)
- open in Zed (thanks @seiichi19881101)
- plus fixes & perf improvements
Most people don't realize how imprecise they are with descriptive language until they try to prompt an LLM to build something
The autistic engineer who normies hate would still listen and reframe their mumbo-jumbo into a considerable offering
The LLMs just go, there are no guardrails for imprecise specs or ambiguous language
LLMs cannot be trusted to provide accurate outputs
Sometimes their magic intersects with pure reality
When that sprinkle of magic mates with reality, it lures people in
It's why we see totally naive hype posts on X all day
Real people building real production software know that apart from these random acts of magic, LLM development is painstaking, constraint enforcement, recursive optimization, redefinitions, bug catches, logic resolution, bouncing down a funnel
Hunk is awesome
🎨 hunk v0.23.0 is out:
- your terminal colours right in hunk (thanks @dhh)
- review GitHub PRs in hunk via `hunk gh pr`
- proper text search via `/` (thanks @elucid_ont)
- open in Zed (thanks @seiichi19881101)
- plus fixes & perf improvements
A lot of LLM output is illusory, it's just shaped properly
Like a house with a beautiful facade but leaky pipes and sketchy electrical wiring
You'll find the errors, painfully, one at a time
Pay now with more thoughtful specs, more human code review, more pair programming with the LLM, or pay later
New blog post: "A sufficiently detailed spec is code"
I wrote this because I was tired of people claiming that the future of agentic coding is thoughtful specification work. As I show in the post, the reality devolves into slop pseudocode
haskellforall.com/2026/03/a-…
Positive vision is not the same thing as anti-vision
Anti-vision is indirectly positive based on what one wants to avoid becoming
Many people masquerade as positives when they're simply fearful, cynical, and resentful
Positive vision weaves and amplifies pure potential, unbounded by fear and resentment
How would you know that your frontier LLM added a persistent config file cache that survives app restarts, and added 6 test cases for behavior that is impossible in the codebase, unless you read the code?
William Belk retweeted
Just one engineer and a team of agents ported the GitHub Copilot agent runtime to Rust, shipping 800,000 lines of production code while retaining code quality. 🚀
How it worked 👇
github.blog/ai-and-ml/genera…
LLMs are all about scope and influence expansion, not knowledge expansion
LLMs don't "know" anything, they just help expand human-constrained shapes and patterns to new frontiers
LLMs in the hands of the inexperienced mind are errant, confused, and unreliable
William Belk retweeted
The "whiteboard defense:" I should be able to pull you aside at any moment and ask you to explain any customer-facing system you've shipped. You should be able to clearly explain how it works and defend the decisions you made. This is my benchmark for responsible AI usage.
I don't expect line-level familiarity with the code. I don't care if you remember the exact function name or implementation detail. You may not even know it. I don't care.
But if I ask "why did you do X instead of Y?", "what happens if this actor behaves maliciously?", "what data structure did you use here and why?", or "where does this fail?" you should be able to answer confidently.
For PoCs, demos, experiments, whatever: I don't care. Generate 100% of it and understand none of it. Speed over quality every time in those specific scenarios.
But if you're shipping customer-facing work, you can't be shipping things you don't understand at a high level.