Nick

building 🌲 🏔️ | fintech | my tweets are my own

[Guillermo Rauch @rauchg]

Coding agents will squeeze every ounce of IKEA effect out of you, if you let them.

[Nick @trannolis]

It’s actually rivaling @AnthropicAI in uptime

[Nick @trannolis]

Great news @cursor_ai! I am looking forward to migrating off @github due to their recent track record….

[Cursor @cursor_ai]

We're launching code storage and git hosting.

Origin gives teams and agents a place to host, review, and collaborate on code.

Available this fall. Join the waitlist.

https://t.co/uamaIarJXY

[Nick @trannolis]

@samlambert lol rage bait

[Nick @trannolis]

"In May, we sent you an email announcing that starting today, the Claude Agent SDK, claude -p, and third-party apps built on the Agent SDK would stop drawing from subscription rate limits and move to a dedicated monthly credit. We're writing to let you know that we’re not making this change today. We’re working to update the plan to better support how users build with Claude subscriptions." @AnthropicAI - stepping back after all the bad press from Fable/Mythos?

[Pablo Zevallos @PabloZevallos]

How it started How it’s going

[notadampaul @notadampaul]

presented without comment

[Cheryl Douglass @cherdougie]

“you look like you’d enjoy Hudson Yards” (derogatory)

[driss guessous @drisspg]

Holy chart crime

[Nick @trannolis]

@Cloudflare is perfectly positioned for the agent economy. I'm running OAuth, Zero Trust tunnels, and Workers handling Streamable HTTP MCP calls back to my servers. The combo of serverless + secure connectivity + native MCP support is insane for production agents.

[Nick @trannolis]

Just published my new note: Economic Observability for Agentic Systems.

Most observability only tells you if the system is alive. Economic observability tells you whether the agent is actually doing its job. Once agents can plan, act, spend, and trade, “it’s running” is no longer enough. A strategy can be fully green while the economic loop is dead. I break down the four ways agentic systems go dark — and the checklist we now use at Pine Peak to catch them early: https://t.co/o8u3dZtyzS.

Would love your thoughts if you’re building or working with autonomous agents.

[Nick @trannolis]

So when are we going to start paying for the AI tax at the provider level? Or does the gov intend to subsidize human labor through tax breaks?

[Mitchell Hashimoto @mitchellh]

I strongly believe there are entire companies right now under heavy AI psychosis and its impossible to have rational conversations about it with them. I can't name any specific people because they include personal friends I deeply respect, but I worry about how this plays out.

I lived through the great MTBF vs MTTR (mean-time-between-failure vs. mean-time-to-recovery) reckoning of infrastructure during the transition to cloud and cloud automation. All those arguments are rearing their ugly heads again but now its... the whole software development industry (maybe the whole world, really).

It's frightening, because the psychosis folks operate under an almost absolute "MTTR is all you need" mentality: "its fine to ship bugs because the agents will fix them so quickly and at a scale humans can't do!" We learned in infrastructure that MTTR is great but you can't yeet resilient systems entirely.

The main issue is I don't even know how to bring this up to people I know personally, because bringing this topic up leads to immediately dismissals like "no no, it has full test coverage" or "bug reports are going down" or something, which just don't paint the whole picture.

We already learned this lesson once in infrastructure: you can automate yourself into a very resilient catastrophe machine. Systems can appear healthy by local metrics while globally becoming incomprehensible. Bug reports can go down while latent risk explodes. Test coverage can rise while semantic understanding falls. Changes happens so fast that nobody notices the underlying architecture decaying.

I worry.

[Kayvon Jafarzadeh @KayvonJafar]

karpathy said “i don’t think i’ve typed a line of code since december” and everyone treated it like a meme.

garry tan treated it like a design prompt: what does it look like when one person runs like a whole software team?

gstack is the first oss repo in a while that actually feels like that answer.

not ai as autocomplete.

ai as CEO + staff eng + qa + security + design + release + browser operator + parallel execution layer, all wired through workflows.

and the number is wild: garry claims ~810x higher pace vs 2013, normalized for logical changes (not fake ai loc).

the shift isn’t “faster coding”.

it’s directing + reviewing + orchestrating a swarm without shipping garbage.

stuff that stood out:

→ /office-hours challenges your product before you build

→ /autoplan runs the CEO/design/eng pass

→ /qa literally drives a browser, finds bugs, fixes them

→ /review catches prod-tier issues before you ship

→ /pair-agent + parallel sprints across projects

we’re moving from “ai helps devs code”

to “devs operate systems of ai workers”.

[Nassim Nicholas Taleb @nntaleb]

A reminder.
As with food, we spent most of our history deprived of information and craving it; now we have way too much of it to function and manage its entropy and toxicity.

[Jun Song @jun_song]

this is honestly so impressive.

last week i gave my codex agent a wallet with $100 and ran /goal make $10k.

one week later, my agent got completely scammed, lost the $100, and the balance is exactly $0.

[Nick @trannolis]

subway thought: I don’t want your SaaS - give me rented access to your agent that is building your SaaS

[Jukan @ ICML @jukan05]

We have only just entered the early innings.

[ry @rywalker]

Anthropic is hunting enterprise workflows to productize. The contrarian bet: a probabilistic system will never match an agent built by someone who deeply understands how their specific company works.

[Sandi Slonjšak @sandislonjsak]

Haven’t met anyone working less after adopting the AI.