Faisal’s Web Site
Sunday, 10 May 2026
claude code is not making your product better
Ethan Ding: “if using claude code gives you a genuine product velocity advantage, and anthropic had it exclusively for 7 months, the gap between claude code and every competitor should be unbridgeable. codex would be irrelevant. instead, people are still actively debating which one is better. the compound advantage isn’t showing up. something else is bottlenecking product quality, and it was never the code”
Programming Is Real Engineering, And AI Proves It
Jeremy Bowers: “Those of us who live in the programming world can end up with a very skewed view of the capabilities of AI right now, because in our world, they are incredibly useful in ways that are much more difficult to extend into other domains. … But now what I consider the basic minimum acceptable engineering for any project that goes into source control is substantially more than was even available to me in 1997. … The AIs bang along all our bumpers; failing compiles, failing tests, failing integrations, error messages, all the bumpers we’ve built into our engineering process, and in the end they get a good result. But that good result is as much a result of all the solid engineering processes we have installed as anything else, because the AI without those protections rolls into the gutter relatively quickly.”
Wednesday, 29 April 2026
Claude Mythos Has Found 271 Zero-Days in Firefox
Bruce Schnier: “No, it’s an extraordinary number […] Assuming the defenders can patch, and push those patches out to users quickly, this technology favors the defenders.”
Monday, 6 April 2026
Significant raise of reports
Willy Tarreau: “Overall I think we’re going to see a much higher quality of software, ironically around the same level than before 2000 when the net became usable by everyone to download fixes. … But before this happens, we have to experience a huge mess that might last for a few years …”
Thursday, 26 March 2026
Keep Deterministic Work Deterministic
Andrew Stellman, O'Reilly Radar: “(It’s possible to reproduce the full compounding-reliability problem in a chat, but a prompt that did it reliably would be far too long to put in an article.)”
Thursday, 19 March 2026
In Search of Banksy
Simon Gardner, James Pearson and Blake Morrison, Reuters: “‘Does an idea belong to those who use it or those who find it?’”
Friday, 13 March 2026
“This Is Not The Computer For You”
Sam Henri Gold: “Yes, you will hit the limits of this machine. […] memory is finite, silicon has a clock speed, processes cost something. You are learning physics. […] The kid who tries to run Blender on a Chromebook doesn’t learn that his machine can’t handle it. He learns that Google decided he’s not allowed to. Those are completely different lessons.”
Monday, 9 March 2026
So You Want to Do Agentic Development
Rui Carmo: “Effective steering isn’t about reprompting and hoping for the best; it’s about funnelling the agent’s attention to the right context …”
The Accidental Orchestrator
Andrew Stellman: “The industry conversation was dominated by agents, tool use, MCP, and real-time reasoning. Batch APIs shipped with relatively little fanfare, but they represent a genuine shift in how we can use LLMs.”
Monday, 23 February 2026
This Is Imaginal Disk
Maia Mindel: “If the AI bet pays off, the labor market implodes. If the AI bet doesn’t, the capital market does.”