infrastructure for AI native work

Worldwide
Joined March 2024
Big update on Pulsar Coffee Meetups. Rome has a new date. ๐Ÿ‡ฎ๐Ÿ‡น Saturday, August 1, 11:30 AM to 1 PM. Hosted by Alex Radu (@Alex__Radu), Pulsar CEO, and Jessy (@13yearoldvc), CSO at @fastxyz. xitter.cf/PulsarMoneyApp/status/โ€ฆ
Wed July 15, Lisbon ๐Ÿ‡ต๐Ÿ‡น Come meet our CMO @kivanarpeev over a coffee (galรฃo, anyone?) Tell us about your dream money app. Learn why we build with Europe in mind, why we chose @arc and get a teaser into whatโ€™s next. We start at 11:00AM. RSVP link in comments
3
7
3
32
11,532
Fast retweeted
The agent economy is in full swing ๐Ÿ”ฅโšก๏ธ and @PiSquared has once again unveiled a fantastic new skill for agents, namely ๐’๐ค๐ข๐ฅ๐ฅ ๐Ž๐ฉ๐ญ๐ข๐ฆ๐ข๐ณ๐ž๐ซ โ€“ a tool that: โ†’ ๐‘‡๐‘’๐‘ ๐‘ก๐‘  ๐‘Ž๐‘”๐‘’๐‘›๐‘ก ๐‘ ๐‘˜๐‘–๐‘™๐‘™๐‘  โ†’ ๐ถโ„Ž๐‘’๐‘๐‘˜๐‘  โ„Ž๐‘œ๐‘ค ๐‘‘๐‘–๐‘“๐‘“๐‘’๐‘Ÿ๐‘’๐‘›๐‘ก ๐ฟ๐ฟ๐‘€๐‘  ๐‘Ž๐‘๐‘ก๐‘ข๐‘Ž๐‘™๐‘™๐‘ฆ ๐‘ข๐‘ ๐‘’ ๐‘กโ„Ž๐‘’๐‘š โ†’ ๐ด๐‘ข๐‘ก๐‘œ๐‘š๐‘Ž๐‘ก๐‘–๐‘๐‘Ž๐‘™๐‘™๐‘ฆ ๐‘–๐‘š๐‘๐‘Ÿ๐‘œ๐‘ฃ๐‘’๐‘  ๐‘กโ„Ž๐‘’ ๐‘–๐‘›๐‘ ๐‘ก๐‘Ÿ๐‘ข๐‘๐‘ก๐‘–๐‘œ๐‘›๐‘  ๐‘๐‘œ ๐‘”๐‘ข๐‘’๐‘ ๐‘ ๐‘ค๐‘œ๐‘Ÿ๐‘˜. ๐‘๐‘œ ๐‘ก๐‘Ÿ๐‘–๐‘Ž๐‘™ ๐‘Ž๐‘›๐‘‘ ๐‘’๐‘Ÿ๐‘Ÿ๐‘œ๐‘Ÿ. This is a tool for automatically evaluating and improving agent guidance, ensuring that tools are reliably used by different LLMs. ๐Ÿ˜Ž Now itโ€™s not just about creating an agent, but about teaching it to work correctly. Now agent skills arenโ€™t just a case of โ€œwriting a prompt and hoping for the bestโ€, but a measurable, optimisable system. ๐Ÿงช One skill โ†’ tested across multiple models ๐Ÿ“Š Metrics โ†’ instead of subjective impressions ๐Ÿ” Auto-iteration โ†’ until it gets better This is the next step: Agents that donโ€™t just exist, but improve. Welcome to optimised agent intelligence โšก #Fast #AI
๐Ÿค Paid partnership
13
5
129
5,244
The builders I respect in this community have all arrived at the same realization: Getting great AI output isn't prompting skill. It's staying organized aka "plan mode", working through a structure, not just dumping the problem into chat and hoping for the best. normalpowers packages that structure. Free, open source, works on Claude (Web, Desktop, Cowork, Code), OpenClaw, Hermes. Adapted from superpowers (the Claude Code plugin) for everyone, not just developers. Tried it on one of our GTM strategies last week. Came out with something actionable. If you've spent hours on an AI session and still got garbage, this is why. And it's a 10-minute fix.
"You wasted all this time and tokens on nothing." every AI user has thought this. the problem isn't prompting, it's that AI answers before it thinks. you get a polished answer to the wrong question. every time. normalpowers fixes the front of the loop. free, open source. think superpowers, but for generalists.
3
6
27
4,305
Fast retweeted
Grigore Rosu
@RosuGrigoreApr 24
Observation after 1 week of running normalpowers on research and planning tasks: The core failure mode in AI-assisted knowledge work isn't model quality. LLMs are optimized to answer, not to structure inquiry first. Give a model an unstructured problem, get unstructured output. normalpowers adds the missing structure: 8 skills that make any LLM ask the right questions before generating output. Works on Claude (Web, Desktop, Cowork, Code), OpenClaw, Hermes. The right frame isn't "better prompting." It's "better epistemics for working with AI." Free. Open source. Worth 10 minutes of your time.
4
6
1
59
3,248
Fast retweeted
Grigore Rosu
@RosuGrigoreApr 24
"Told you to first understand the problem well, and then answer." Each time I blamed the model ... "next version will be smarter". Truth is that good communication skills and asking the right questions are often more effective than intelligence alone. Both for humans and for AI.
"You wasted all this time and tokens on nothing." every AI user has thought this. the problem isn't prompting, it's that AI answers before it thinks. you get a polished answer to the wrong question. every time. normalpowers fixes the front of the loop. free, open source. think superpowers, but for generalists.
5
6
1
35
3,392
Fast retweeted
Grigore Rosu
@RosuGrigoreApr 22
11
14
69
5,036
Fast retweeted
we used skill-optimizer to optimize the skill that we're now shipping with skill-optimizer talk about inception... also here's how the optimization process went๐Ÿ‘‡
skill-optimizer 1.1.0 is here โœ๏ธAdded prompt surface as a type of tool the skill can be optimized for ๐Ÿค–Added Codex auth ๐Ÿง‘โ€๐ŸซBundled SKILL/ guidance to allow AIs to easily use skill-optimizer ๐ŸงนGeneral code cleanup and architecture improvements github.com/fastxyz/skill-optโ€ฆ
3
6
25
3,355
Fast retweeted
this tool is a stupidly simple loop: insert tool + skill, let LLMs use it, benchmark performance, improve, repeat and it's now open source. try it, contribute to it, file issues, have fun:
5
1
18
1,873
This is pretty cool, so thought I'd share! We took our payment skill from ~60% success on weaker models to 90%+ in around 3 hours for about $5 on OpenRouter Thatโ€™s a ridiculous trade
we built skill-optimizer so anyone can ship good agent skills without wasting time on trial and error. now weโ€™re open sourcing it to make skills easier to evaluate, improve, and adapt effortlessly across multiple LLMs. repo link โฌ‡๏ธ
6
1
19
3,577
Fast retweeted
Grigore Rosu
@RosuGrigoreApr 14
A good idea that works becomes a skill. A skill becomes automatable agent work. Skill Optimizer is an agent orchestrating other agents to craft the optimal skill for the job together. Result? A skill that works with all agents.
we built skill-optimizer so anyone can ship good agent skills without wasting time on trial and error. now weโ€™re open sourcing it to make skills easier to evaluate, improve, and adapt effortlessly across multiple LLMs. repo link โฌ‡๏ธ
4
11
37
2,538
How do you build a network for Agentic Payments? ๐Ÿค– @PiSquared married two breakthroughs: a 2019 method to solve double-spend without a blockchain, and Grigore Rosu's EVM formal verification. The result: A lightning-fast, mathematically proven execution layer. โšก๏ธ
12
9
2
52
3,816
A Citizen's Guide to Driving Blockchain Policy by @JeetRaut, Head of Strategy of @PiSquared 2026 will be the most consequential year for U.S. blockchain policy in history. This talk gives attendees practical tools to shape outcomes, including how bills move, who influences them, and what actually motivates policymakers, from jobs and taxes to voter impact. Full video below ๐Ÿ‘‡๐Ÿงต
13
8
8
50
5,273
Fast retweeted
First day in Denver! Our VP & Head of BD @lei_lei0904 joined @wrappedxyz's Multichain Day with top builders from @0G_labs , @PerleLabs , and @PiSquared to dive deep into the future of onchain AI infrastructure, from verifiable compute and data provenance to the payment rails powering the agentic economy. ๐Ÿ’กKey highlights: โ€ข AI x crypto remains strongly bullish despite uncertain market conditions โ€ข Kiteโ€™s Human-Agent-Session architecture enables secure, low-fee micropayments purpose-built for agents โ€ข The shift from black-box models to decentralized, verifiable systems โ€ข Panel insights on storage, data labeling, and formal verification challenges โ€ข Agents are chain-agnostic and focused on getting tasks done efficiently โ€ข Spicy takes on training data scarcity and the future of social media Letโ€™s keep pushing the boundaries. ๐Ÿช
15
35
1
130
15,201
We confuse the destination (Web3) with the vehicle (Blockchains). ๐Ÿš— @PiSquared drops a spicy take: AI agents will integrate massively with Web3 and Crypto, butย notย necessarily with blockchains. Blockchains are just a mechanism. The infra has to evolve to survive. ๐Ÿค–
7
7
4
43
6,323
Fast retweeted
Total ordering is killing every blockchain you're invested in. No one talks about it because most don't even understand it. Fascinating deep dive with @RosuGrigore on how @pisquared is solving Web3's biggest bottleneck: ๐Ÿ”นInteroperability ๐Ÿ”นScalability ๐Ÿ”นThe ordering problem that breaks at scale From NASA engineering to 160k+ TPS on FastSet, the math doesn't lie. Masterclass on what actually comes next: ๐Ÿ‘‡ 1:30 โ€“ From NASA to Web3 3:39 โ€“ The Elephant in the Room 4:54 โ€“ What is Pi Squared? 12:06 โ€“ Introducing FastSet 17:42 โ€“ Why Not All Apps Need Ordering 24:46 โ€“ Interoperability by Construction 34:11 โ€“ Language Agnostic Web3 36:24 โ€“ Hitting 150,000+ TPS 42:15 โ€“ Introducing Omniset 50:40 โ€“ The Steam Engine Analogy
9
21
81
4,288
why we back @PiSquared? 1/ because it creates a new category, not another blockchain, in fact "not blockchainโ€ at all, but a fully parallelized execution network where transactions are mathematically verifiable and can run without artificial dependencies 2/ on top of that, Pi Squared is shipping a stack we have not seen combined before: fastset for capital efficiency, Omniset for intent-based, bridgeless liquidity across apps, and a payments and markets layer that finally gives builders unified building blocks and a great interface 3/ most networks still force the world into queues. @PiSquared is built different, around how reality actually works - independent actions in parallel. this is the first meaningful step beyond sharding toward how scalable systems should really operate in web3
6
8
52
2,488
Fast retweeted
Grigore Rosu
@RosuGrigoreJan 3
The so called "blockchain trilemma" incorrectly identifies the three fundamental principles of Crypto/Web3 with blockchains: 1. Decentralization - this is what makes the system unstoppable. Unstoppability is the only reason we talk about decentralization. Censorship-freedom is a corollary. This goes beyond blockchains. 2. Security - this is what gives us true ownership of our assets. Private/public key cryptography, verifiability (formal or not), soundness / consistency of protocols, etc., are just mechanisms to realize it, which all go well beyond blockchains. 3. Scalability - this is what makes the entire thing practical. To be future-proof and scale to the entire planet, including both humans and AI agents, we need infinitely scalable infra. Period. Blockchains are a particular instance of strongly consistent systems, which are known to not scale. Tribalisms and strongly opinionated CT folks and biased investors cannot change facts. If you want to change the world for the better, look at fundamentals and build your and our and our children's future on solid principles and values. This is what give life meaning, after all. We cannot have freedom without financial freedom. Or ore generally, without truth freedom. Indeed, _truth_ is main value that we need to express and convey. The rest is details. And for that we need unstoppability, security, and infinite scalability. This is what FastSet is all about.
29
10
8
95
5,768
Your liquidity is fragmented across 10 chains. @RosuGrigore and @PiSquared built OmniSet to fix that. One wallet. All your assets unified. Verified in milliseconds. No bridges. No trust. Just math.
15
18
2
119
6,471
โ€œIs it an EVM chain?โ€ First, itโ€™s not a chain. Second, hardwiring a language is stupid. @RosuGrigore on why FastSet by @PiSquared rejects EVM and lets developers use any language. Full interview ๐Ÿ‘‰ youtu.be/tzIAJmYzM_o
13
17
1
102
5,162