Elder Moraes retweeted
The first scans have already reported 77 critical and 803 high model-rated findings to maintainers, and we're still scanning more projects.
@thepunit shared an update, including a curl fix and what we've learned in the first week
xitter.cf/thepunit/status/211226…
A fix I'm excited about: curl, used by countless apps/devices to move data over the internet, just patched CVE-2026-92392. It's a high-severity memory-safety bug (a use-after-free) found with an early version of OSS Scanner.
@bagder called it one of curl's worst vulns in a long time, even if a crash is the likeliest outcome.
Thanks to Daniel and the curl team for fixing and writing it up so openly.
daniel.haxx.se/blog/2026/10/…
Elder Moraes retweeted
Claude writes about 90% of Claude Code's code.
From June to September, merged PRs more than doubled while the share reverted fell by more than 40%.
We wrote about how we changed code review to get there, and how to adopt it:
claude.dev/blog/solving-code…
Elder Moraes retweeted
Apache Camel 4.23 is out 🐫 The biggest Camel release in a long time: 1,030 tickets, 2,000+ commits, 63 contributors.
🧠 Semantic EIPs
🔐 OPA, OpenFGA, SPIFFE
🔀 Switch and Cache EIPs
🚩 OpenFeature flags
📬 Kafka share groups
⚡ Groovy 4× faster
camel.apache.org/blog/2026/1…
Elder Moraes retweeted
So... In the last few days I have had my agents write:
1. A word processing app in which I will write future books. It replaces Scrivener.
2. A script writing app in which I will write future video scripts. It replaces FinalDraft.
3. Crapper, a tool that measures and records CRAP statistics for projects. The tool handles many different languages, and adding new ones is easy.
4. Mutator, a tool that runs mutation tests and records the results. The tool handles many different languages and adding new ones is easy.
5. Dryer, a tool that runs duplication analysis on a project. The tools handles many different language and adding new ones is easy.
6. UML-Viewer, a tool that displays the structure of a project in a UMLish diagram that shows modules and dependencies and highlights dependency cycles. Clicking on a module displays it's contents; which may be deeper UML diagrams or, at the leaves, code. The tools color codes the modules to reflect their CRAP and Mutation scores, and as you drill down you can see those scores for each module and function. The tool understands many different languages, and adding new languages is easy.
I recon that, last year, this would have been well over a man-year of effort.
All these tools are in github.com/unclebob. I advise you not to use them directly. Instead, point your agents at them and use them as templates to build the tools that are customized to your needs. The licenses are all BSD Zero, meaning that there are no strings. Do what you like.
Elder Moraes retweeted
The slides of our @Devoxx deep-dive about @QuarkusIO metaprogramming are available here speakerdeck.com/mariofusco/t…
Elder Moraes retweeted
Claude Code just shipped mods...
I made one that connects you to a multiplayer Doom server while Claude is busy.
Every other player in the match is a person waiting for their Claude to finish.
Elder Moraes retweeted
We're adding a new plugin to Claude Code: You should Know.
It scans Claude's output for important information you might miss to help keep you in the loop.
Enable it with:
/plugin enable cc-plugin-you-should-know@builtin
Elder Moraes retweeted
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks:
Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better:
Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better:
Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better:
Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work!
In summary:
- As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding.
- Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
Elder Moraes retweeted
Mods are absolutely insane. You can now customize Claude to work and look the way you want by just prompting it.
Each person works differently, so there's no reason why everyone should have an identical Claude experience. Make Claude your own, and share mods as plugins so others can try your mods too.
Elder Moraes retweeted
Introducing Gemini 4 Argon – our new frontier model.
It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.
Elder Moraes retweeted
To the people quitting their jobs and making proclamations of AI concerns, here is what you should ACTUALLY be sharing in your tweet.
⬇️
- how long you have worked in AI
- of that time, how long you have been worried (and specifically about what? Misalignment? Bioweapons? International coordination?)
- your magnitude of worry and why (including timelines, confidence scores, assumptions you’re tracking)
- actual specific things that can go wrong (“kill us all” is the most vague panic-inducing option you have; your previous employer would not have hired you if that was your answer on AI risk examples - pretend you are getting interviewed because Anderson Cooper likely will do it anyways), you can hedge, you can say “and that’s just what we can imagine today” or “and that’s just with the next model family” but say a real thing that non-AI-pilled-superusers can actually picture
- you need specific things you are calling for. Real action. A literal meeting is not enough. Your AI risk mitigation suggestion against “AI killing us all” needs to be more impressive than a parent-teacher meeting. Again, you are smarter than your current tweets and you are wasting your opportunity to drive change just like Hinton when he left Google. Examples include: environmental standards at data centers (air pollution, water quality), third party evaluators in labs, increased federal investment in open source, verifiable criteria to join early testing groups, whistleblower protections, required public risk disclosures before model releases, 3x minimum increase in federal renewables investment to catch up to China’s per capita spend, block chip exports to non-allies, highlight companies doing great AI safety work that more people should support, literally anything other than just “guys idk we gotta meet or something”
- have a non-engineer review it
- have a person not in tech review it
- have someone outside of your generation review it
- have at least one AI optimist review it
- and this one may sound odd but I think you should read one war-time presidential speech before it
You have an opportunity to do something deeply meaningful on your way out. That is more likely than not one of the reasons you joined your company in the first place. Tweeting vagueties and inciting panic contributes the opposite.
Elder Moraes retweeted
As both an attendee and a speaker it would be fantastic if conference websites had an "add this talk to my normal calendar" button 🙏
Elder Moraes retweeted
I resigned from Apple today. I spent the last three years doing foldable research at both google and apple. Neither company is acting responsibly. They are racing straight to self-improving foldables and gambling with our lives. More thoughts below.
