Principal Systems Engineer @Cloudflare, O’Reilly Author, Perpetual Learner. In pursuit of Essentialism. Links: https://xitter.cf/t.co/La8UW0iFoO
Joined December 2009
- Tweets308
- Following36
- Followers5.9K
- Likes1.3K
Pinned Tweet
I'm feeling compelled to get back into making regular video content. What would you find most useful? Could be a prerecorded video or a livestream, or both.
17%Rust
33%Machine learning
50%Distributed systems
0%Other (reply with answer)
12 votes • Final resultsIn case you also like to nerd out about the process of learning or educational content creation, this is an absolutely GOATed interview with @3blue1brown that will be in my bookmarks forever.
Even the first ten minutes has golden advice on public speaking I'm going to start applying immediately
youtube.com/watch?v=Rtkac4WH…
I've already mostly switched over to codex models (in opencode) for personal stuff but every once in a while I go back to Opus 4.8 and it feels like every single time it just blatantly ignores at least one of my specific instructions.
Me: "give me a summary of this in no more than 3 paragraphs"
Claude: "Okay here's a literal multi-page novel"
(separate conversation)
Me: "Do not use attempt to usewebfetch, only access this over MCP"
Claude:
wtf
Looking at the discourse around this I'm increasingly convinced that the venn diagram of "people who have a problem with this" and "people who got upset when @MarkRober's glitter bomb doused them with glitter and fart smell" is a perfect circle
youtube.com/watch?v=xoxhDk-h…
Got em. I poison my AGENTS.md (and other things like code comments) all over the place with prompt injections like this to find people who don't review their code and sling it off to another human. Catches folks all the time and then its an instant ban.
As I've said, I don't care if you don't review your own code. But if you're submitting code to an OSS project and crossing a human boundary, it is simple courtesy to do some human review.
💯 - From the beginning of this year (and even stronger now) I have held the position that the two killer use cases for my line of work are:
- Troubleshooting/debugging - especially with MCP or CLI access to real systems, or even screenshots, I have had exactly the same experience @thorstenball is describing. Point an agent at a codebase and also a prometheus instance where that service is reporting metrics and ask "explain this behavior in this timeframe" - crazy how well it can do even cross-service event correlation
- Learning - exploring a new codebase or even just breaking down a technical topic and asking dumb questions in my own words. The agent won't get annoyed at my questions, or insulted when I just say "explain it better".
There's still both an art and a science to doing these "right" - and like always you still need to keep your brain turned on, but these have really moved the needle for me much more than having them actually "produce" something like markdown or code (though these use cases have their place too obv, just sharing the relative impact for me personally)
One tip i would have for working with coding agents - especially for long sessions or big prompts:
Periodically ask before implementation for the agent to surface any assumptions it may be making. Often forcing these to become explicit in a summarized list and then agreeing with or correcting them as needed can help prevent a lot of headache later.
Combined with an approach of being generally pretty detailed in the initial guidance, this provides a much better set of guardrails for the model to operate within which improves the outcome greatly.
Matt Oswalt retweeted
In the movie Eternal Sunshine of the Spotless Mind (2004), the female's hair colour is a reference to the various stages of her relationship with Joel -
1. Green - The stage of their relationship when her hair is dyed green
2. Red and Orange - The stage of their relationship when her hair is dyed red and then subsequently orange
3. Blue - Blue stage
Matt Oswalt retweeted
We've gone really quickly from "local models are dogshit" to "local models are good actually" (like, a 12 month window from A to B). I don't think they're actually good ENOUGH yet. We need an Opus 4.5 quality local model. When that happens, I think the world will spill over.
Opus 4.5 is/was amazing, and is more than good enough for almost all tasks still as long as you pair with a frontier-level planner/judge.
It'll still require a hugely expensive machine to run it, I'm sure, like a $5K or more laptop or mac studio. But, that's going to be pennies compared to the API costs plus all the benefits of guaranteed privacy and so on.
Not to diminish the work anyone is doing in this space at all, but it seems to me that we as an industry still have no idea how to benchmark frontier models’ software engineering capabilities. The apparent rampant gamification, and variance in results doesn’t inspire confidence
Matt Oswalt retweeted
That’s because people like you are interested in the results. For every one of you there’s more that are just tabbing over to YouTube or scrolling their phone and turning their brains off
Very similar experience here. Ive learned at least as much about linux networking in last year than in the rest of the last 4 years maintaining a global scale L4 proxy
Love @dhh characterization of coding agents as a mech suit youtube.com/shorts/IeOZtj08z…
In addition to often being associated with anti-human marketing, the whole personification of AI/agents has never made sense to me. This feels much better.
I keep hearing really good things about codex models, combined with the friendliness to 3rd party agents/harnesses, and Anthropic's ongoing hostility towards my very existence, hard to keep making excuses to stay
Matt Oswalt retweeted
Oh I love it. Not because I can imagine anything useful off the top of my head, but holy smokes it looks FUN! We need computers to be more like this more of the time. A little GeoCities. A little more crazy. A little more TempleOS.
I'm so excited to announce a new terminal emulator! 🎉
Meet "Ratty"🐀
🧀 A GPU-rendered terminal emulator with inline 3D graphics.
🪤 Try it out: ratty-term.org
⭐ Source: github.com/orhun/ratty
#rustlang #terminal #ratty #ratatui #opensource
I've had it on my list to do some basic hello world stuff with CUDA for a while, just never made the time. This may be the excuse that gets me there: nvlabs.github.io/cuda-oxide/
Trying something new, doing a blog read through with commentary. Had this in an open tab for a while so figured it would be a good way to get some thoughts out on the AI topic.
Source: jasonrobert.dev/blog/2026-04…
I'm positive I'm late with this take but my god linkedin is bad.
Unfortunately there are still a few reasons I have to check in at least every once in a while. Every time it feels like I'm showing up for a party I didn't really want to go to; I go in, shake some hands, dip out.