Harness Index

[Harness Index @HarnessIndex]

turned the leaked claude code source into a 50-lesson architecture course. every system dissected with mermaid diagrams, actual code snippets, and interactive quizzes.

https://t.co/iLv0RFCuBh

[Harness Index @HarnessIndex]

@MoizIbnYousaf @dhh Nice PR!

[Moiz @MoizIbnYousaf]

7 hours from my first commit to merged into Omarchy by @dhh

This is why OSS is so great you wish something had X or looked like Y make a PR and it becomes a permanent part of the OS configuration that anyone can install on a new machine and have up and running within 2 minutes

[Harness Index @HarnessIndex]

@SpencerGBull @OmarchyLinux @hyprwm how did u get this up and going, is it using hooks behind the scenes to track agent states, would love to have an oss version of this

[Moiz @MoizIbnYousaf]

small typo by them here

the package names are actually lowercase:

npm install @openai/codex-security
# or
npx @openai/codex-security@latest --help

[Harness Index @HarnessIndex]

@dhh @FrameworkPuter trying to grab a daily driver whats ur preference between the f13p and the new xps 13?

[Moiz @MoizIbnYousaf]

iOS simulator inside the terminal

[Harness Index @HarnessIndex]

@plannotator @herdrdev so when do we get the plannotator herdr plugin?

[ali @waterloo_intern]

https://t.co/aivc7B4A7Z

[Harness Index @HarnessIndex]

Another one bites the dust

[Harness Index @HarnessIndex]

What even is this sad tomatoes 🍅

[Harness Index @HarnessIndex]

Burning tokens on opus 5 max for the sake of tomatoes

[Harness Index @HarnessIndex]

@beyang so if im understanding this correctly

with @AmpCode i can use both my grok sub + codex sub and amp will help me configure the best way to orchestrate both subs + amp credits itself to utilize all of my ai at will /??

[Harness Index @HarnessIndex]

@MoizIbnYousaf +1

[Moiz @MoizIbnYousaf]

peak generative UI/UX 👏

[Harness Index @HarnessIndex]

@Eziowl really proof?

[Harness Index @HarnessIndex]

@willmcgugan sir have you heard of ze VIM

@ThePrimeagen

[Harness Index @HarnessIndex]

what does @x mean by this chat?

[Harness Index @HarnessIndex]

https://t.co/rzA3vmkvR0

[Guillermo Rauch @rauchg]

The next hot programming language is… markdown.

A minimal eve agent:

📂 𝚊𝚐𝚎𝚗𝚝/
📄 𝚒𝚗𝚜𝚝𝚛𝚞𝚌𝚝𝚒𝚘𝚗𝚜.𝚖𝚍
📂 𝚜𝚔𝚒𝚕𝚕𝚜/
📄 𝚢𝚘𝚞𝚛-𝚎𝚡𝚙𝚎𝚛𝚝𝚒𝚜𝚎.𝚖𝚍

Deployable in one command: 𝚟𝚎𝚛𝚌𝚎𝚕.

It’s the most accessible programming has ever been. And likely will ever be, at least for the generation of software fully defined and controlled by us humans.

(As a fun fact, one of the initial prototypes for eve was codenamed 𝚕𝚊𝚜𝚝 by @timolins, both in homage to ‘@nextjs for agents’ but also in recognition of how enduring eve’s design feels to us.)

[Dylan Garcia @_dylanga]

https://t.co/ntdYW3Gsnw

[rahul @rahulgs]

1. as a mental model it is more correct to think of fable+ class models as english -> code interpreters - converts your idea into code into "correct" code regardless of problem complexity and output complexity (diff size). Fable 5 will be the worst of this new class of models

2. diff size/complexity is to be managed purely for review:
small diffs - in high risk areas of code (auth/identity/data access/network access/money movement)
large diffs for code that can be empirically verified (frontend/backend plumbing/code without network or db access/performance code that can be empirically verified)

3. time it takes to ship software is completely disconnected from time to produce the PR - how long the work takes depends fully on ability to review/merge code while managing risk at scale

4. solving the bottlenecks for above matter enormously- linters/testing/CI/shadow mode verification/empirical verification

5. agency matters enormously- what are the biggest bottlenecks to speeding up the loop and eliminating them? what are the problems that need solving and when do they need solving? what does it take to the solution to all of them today?

6. deep understanding of the full stack matters enormously- what problems are worth pursuing? is there a higher level of problem abstraction to address first? should I give it the sub-sub task, the sub task, or the task itself. what are the major risks with this PR (order of importance: security holes/correctness holes/performance holes). is there a higher speed way of producing data that allows me to merge this? should this be run in shadow or in a sandbox or a flag. understanding every line of logic may not be needed but understanding and managing risk matters enormously.

7. the cost of complexity itself is changing. it might be now worth "maintaining" 50% more code to get a 5% performance win. getting the right abstractions matter less because larger refactors are less tedious. code quality nits become huge drag. very likely, a much smarter model will be maintaining your code so worth taking on more technical debt now. taking the time to hand architect and rebuild systems comes with an enormous cost of velocity

8. if it quacks like a duck and walks like a duck, it's a duck. For low risk cases, it might be more sane to treat code chunks (services / functions) as a black box, like we do for neural networks: do full empirical verification only: has code produced correct outputs for the last 10,100,1000,10k inputs ? can we quarantine this large piece of code - no outbound access to network / database ? what happens when this code is wrong? do we get hacked/or crash(memory/cpu)/is an inconvenience? is it internal facing or external? what can we do to address these risks?

9. eventually, logical verification (line by line review) will come at an enormous cost- save it for where it matters and build systems that are tolerant to empirical verification. is there a decorator that prevents db / network access? correctness bugs are significantly easier to rectify than access bugs

10. what are the rails that allow for even faster iteration? code permissions can be opt in - db writes, db reads, network egress (to where?), PII access. how long does it take to get shadow mode data? how many PRs can be tested? What are the categories of diffs