Darian Moody (@djm_) header
Darian Moody (@djm_) profile picture

building bits, dabbling with ai. generalist across teams, perf, ui, security. past crimes: cto @ yunojuno; 10y+ xp contracting @ startups, agencies & faang.

London, England
Joined July 2010
"Purchases and downloads have not doubled". Discovery is going to be even more important in the era of slop.
The number of game pages being created per day has doubled in the past 2 months
75
Darian Moody retweeted
I enjoyed this One Weird Trick someone shared on the HN thread about the Northflank breach: news.ycombinator.com/item?id…
1
2
26
2,134
Darian Moody retweeted
models have no sense of time. they'll trigger a 30 min rebuild for a 2 line change instead of thinking ahead and batching the work current frontier RL rewards token efficiency future RL will reward time efficiency the fast takeoff will feel absurd after this
65
41
16
1,480
134,446
Reeks of the touchbar again. ngmi.
how is this the hero use case they advertise for the touchscreen MacBook Pro who is doing this
1
90
Darian Moody retweeted
Day 28/ Julius cooked harder than I thought. Multi-machine orchestration has been achieved internally. One thread, multi-model, multi-harness, multi-app, multi-os, multi-machine, multi-network. We're just getting started :)
Day 27/ Run into a bug? Debug it in t3 code itself with cmd+k "triage" This will: - Clone the T3 Code source for your exact version - Give context with a playbook to your agent of choice - Let you debug and fix the problems with your agent - Cut an issue if it's our fault
248
67
55
2,959
337,689
In time, resets will be seen in the same pool as other dark growth marketing tactics like: * excessive red pips * stealing contact books Crack dealer behaviour tbh.
hello from literally everybody who took psychology 101 in undergrad
1
1
93
Darian Moody retweeted
hello from literally everybody who took psychology 101 in undergrad
Replying to @AdamHoltererer
I honestly don't get the obsession with limit resets
38
7
4
133
14,083
is this a teaser.
feels like there needs to be a new way to distribute opensource software such that people can modify via agents but also get upstream automatically merged in coding agents can do this but they won’t do it automatically
96
Small announcement: ✅ formal-git As an experiment, over the last 2 months we've modelled ~30% of Git in Lean 4, making heavy use of coding agents, and proved >8000 theorems of varying usefulness about the implementation. In the process of doing this we've uncovered >100 potential defects in Git v2.55, at least two of which may constitute security vulnerabilities. We've also built a DRT (differential random testing) harness and the biggest corpus of relevant pinned differential test cases for Git implementations with >10k unique tests at the moment. We've used the test cases to test our own small internal implementation of Git in TypeScript. The next step will be to differentially test all notable public Git implementations against this corpus of tests to help improve their correctness and security 🫡 We'll be reaching out to library maintainers in due course. If you have a Git implementation you'd like us to help you test, please reach out and let me know. We'll open-source all this eventually, after potential security issues that were uncovered are responsibly disclosed and fixed.
39
66
10
551
25,313