⬅ Mathew Hartley retweeted
Now you can really see everything
NZ based, and having fun with a hermes bot doing product research and daydreaming on what if projects for me - but that's powered by OCG and deekseek flash so I'm not spending more than $50USD personally for the privilege (~$500USD for work, monthly)
This really resonates with me
I have zero desire to have agents triage my email, go shopping for me, analyze my kid’s homework or whatever
I’m not mad, these are just not problems I have that need solving. And lmao that most of this crap comes from grifters 😂
1
78
⬅ Mathew Hartley retweeted
Got rejected from a @Railway job this morning because I put “we should not breach our customers” in my resume.
⬅ Mathew Hartley retweeted
Canva’s terms for departing employees are both exceedingly generous and a window into modern tech:
* Six months salary
* A year healthcare
* A year of LinkedIn premium
* A $10k grant to start a business
* Keep your MacBook
⬅ Mathew Hartley retweeted
New portfolio site, lovingly vibe coded elliottkember.com/
⬅ Mathew Hartley retweeted
We got your back, New York!
Readers added context they thought people might want to know
Several figures here aren’t federal results or NY-specific. The $472B combines US wide pledges: Micron's $250B is nationwide (NY site $100B) Anthropic's $50B covers TX and NY. The 48% murder drop is from NY's state run GIVE program (28 departments, Jan – May 2026).
arkolith.com/news/news-micr…
therepublic.com/?p=843020
governor.ny.gov/news/safer-str…
⬅ Mathew Hartley retweeted
recommended reading. i have many feelings about this.
rikiyat.github.io/blog/weigh…
Pretty sure in May I had a staff eng ask me to revert to avoid the merge conflicts my refactoring had caused for a long-running pr
1
64
strong agree
Replying to @wangzhr4
• comments go stale very quickly and confuse agents and people
• they are often used by agents to explain workarounds that would've been better off actually fixing the code instead
• they are not enforceable and waste your agents' tokens
my point is that moving prose (comments, rules, agent.md, skills) into deterministic lint rules, better API design/types, is far more effective, enforceable, and token efficient.
comments are simply a crutch that agents will happily misuse
53
Here's some takes on Agentic Dev:
- Force your agent to comment like they're being graded. Allow them to clean up nearby comments too
- Ask for the subtractive fix
- Delete tests that restate the code (Tautological tests considered harmful)
- use t3code nightly
what's yours?
1
3
175
Other side of this is the most valuable devs from 2+ years ago might not be the most valuable today with how far software dev has shifted
it's crazy how easy it is to spot 10x engineers these days
for a certain set of people LLMs totally unlocked their potential
to the point where imagining their life before this seems totally depressing
49
⬅ Mathew Hartley retweeted
Just told Claude to have some "me time" and work on something that it would enjoy.
Got inspired by UniiChat by @VictorTaelin so vibed a plugin for my Hermes bot - github.com/fourseven/hermes-…
(still back porting my history across though 😅)
Lemme know if this is useful for you
93
⬅ Mathew Hartley retweeted
🗞️ the world hasn’t figured out yet that you can literally just fix everything with a Nix overlay
In this blog post, I go into how I use Nix, why you should use it, and in the tweet below is a runnable demo showing all of the concepts in this post ghuntley.com/nix/



























