0xF

[0xF @0xfisnik]

@realDonaldTrump Stop it. You’re draining my battery with these stupid posts.

[0xF @0xfisnik]

@DesheShai Why didn’t you add a question mark to your ‘why’? 😜

[0xF @0xfisnik]

@cu30rry_ @poteto are you into this? :D

[0xF @0xfisnik]

@Crypto_BitC what about $100,000? what might it be? Transcendence?

[lauren @poteto]

it's easy to fall into the trap of micromanaging your agents instead of correcting the environment that shapes its behavior.

pstack 0.15.9 now ships a new /correct skill: if you keep correcting agents for the same mistakes, it finds the pattern and fixes it with architecture, types, and checks.

i like to imagine that commits rapidly flowing into the codebase are like a bonsai tree rapidly growing in whatever direction it pleases. what you want to do is not to give in to the chaos, but tame it intentionally with the right constraints

0.15.9 also has improvements to:
• /architect: now includes instructions on designing agent friendly architecture
• a new /benchmark-checklist skill based on @brendangregg's benchmarking checklist

here's a prompt you can give to grok bot to start architecting a better codebase with pstack:

/poteto-mode create a new Project agent to refactor and rearchitect my repo so that our architecture is more agent friendly. it should use both the /correct and /architect skill to look through past commits and find the most common pitfalls that agents fall into, whether its with code quality, performance, or bugs. if relevant you can also use the /recall skill to find past conversations for context. it should make a high level plan for me to review. it should also answer its own open questions by prototyping rather than defer to me. come back to me with a plan backed by real data. once i approve the plan, use either the stack or full autopilot playbook (ask me which i want) to execute

[0xF @0xfisnik]

@FitimCeku e cka leshin na duhet ky hajn per Kryetar shteti? pse kta tjert a nuk jane shume pro Amelikan a?

[Ayaan 🐧 @twtayaan]

AWS is coming for the cloud architect’s job.

Or at least, a big chunk of it.

They built an AI agent that can audit up to 100 AWS accounts, find architecture problems, and generate the Terraform fixes for them.

The new Well-Architected Agent checks cost, security, performance and resilience across 65+ AWS services.

Feed it Terraform, CloudFormation or CDK, and it can return the IaC changes and CLI commands needed to fix what it finds.

And it doesn’t stop after one review.

AWS says it can automatically re-check your environments every week.

Full announcement: https://t.co/GUlrVzjO2X

[James Ward @JamesWard]

My super slimmed-down AWS console is Claude Code with the AWS Agent Toolkit.

[Satoshi Flipper @SatoshiFlipper]

$NEAR 👏👏

BOTTOM IS IN 🎯

[0xF @0xfisnik]

@czbinanceprd $KAS

[0xF @0xfisnik]

@binance __SHIT__

[Josh Long @starbuxman]

a free algorithms course taught by a CMU professor. Been ages since I've revised my algorithms knowledge. I wonder how I'll fare and what I can learn.

https://t.co/O6Lb0lt2G8

[0xF @0xfisnik]

@Nebraskangooner ivermectin for what?

[0xF @0xfisnik]

@trader1sz @Shirink_13 @grok stupid request :D

[0xF @0xfisnik]

@juliendubois @Stephan007 Looks sick 😀 keep this pls

[Vivek Galatage @vivekgalatage]

Algorithms by Jeff Erickson - one of the best algorithm books out there.

The illustrations are simply great - I highly recommend this.

https://t.co/8G06RjGnMA

[Alex Xu @alexxubyte]

Do you think the SOLID principle is still useful in the age of AI?

[Argona @Argona0x]

whoever leaked this has bigger balls than sense

two researchers replaced $7,500 of human grading with $77.81 of model calls, and the number that fell out should stop anyone shipping an agent this week: the judge disagrees with itself 13.6% of the time

it also prefers whichever answer it saw first, 72% of the time. cross-judge agreement is a kappa of 0.51: the statistical polite word for guessing

this is Eval Engineering, the layer that arrives after loops and graphs, and it installs into the agent you already pay for:

- run every comparison both ways and average the two, because one production judge picked whichever answer sat in the first slot 72% of the time
- stop shipping on a single verdict: recovering the reference answer took 11 repeated trials before a majority vote landed it, and 15 on the questions that actually mattered
- report the chance-corrected agreement instead of raw match, since the gap between those two ran 33 to 41 points on the same benchmark
- never let a model grade its own family, because self-preference tracks capability upward rather than falling away as models improve
- test stability and bias together, since two judges already running in production held above 0.95 on repeat while carrying severe positional preference
- freeze the rubric wording and version it, because semantically identical templates flipped the majority outcome in a quarter of tested cases
- write the rubric as one observable pass condition rather than a bundle of scores, so a coin-flip preference cannot hide inside an average
- let plain code take every objective call, did the test pass, does the file exist, did the state change, and leave the judge only what genuinely needs reading
- make the verdict do something structural to the run in flight, reject the handoff, swap the node, quarantine the branch, or you have built a dashboard

the catch is that your judge is a measurement instrument nobody calibrates: single-trial judging is too noisy for anything you would stake money on, and the same judges reordered by as much as 14 positions depending on which benchmark you asked

so the loop has to converge on the spec rather than on the score, because optimise against a judge long enough and the agent learns to look right instead of being right

bookmark this, the full build with the five evals to start on and the gate that lets the fleet merge its own work is written out in the article ↓

[ClaudeDevs @ClaudeDevs]

MCP 2026-07-28 is live and it's the largest update to the protocol since launch.

MCP is now stateless, making it easier to deploy and scale remote servers.

https://t.co/K8KqxbUh4e

[0xF @0xfisnik]

@larrythesender @RobinhoodCrypto Yeah, just gonna send it ..but this way 📉