Agents, audits, loops & logic

Joined June 2014
Mr.Matching retweeted
An update on FlockFall I shared this yesterday in Discord, but everyone following here deserves an update too. Land will not launch. I’ve decided to wind down the current version of FlockFall, with another 30–60 days of support for the game. I know this is disappointing. I want to explain what brought me to this decision and what happens next. WHAT CHANGED FlockFall started as an experiment in fully on-chain gameplay. I wanted players to be able to verify ownership, rewards and outcomes instead of simply trusting me to get them right. I tested for almost two months under much lower gas conditions, without encountering the spikes that appeared around the transition to mint and mainnet. I continued optimizing after launch. Those improvements helped, but live operation exposed limitations that go beyond gas prices alone. THE UNDERLYING PROBLEM • The game needs ongoing transactions to process progression, outcomes and returns, including during quieter periods. • Players pay costs in ETH while earning SHELL. Lower SHELL prices or higher gas can make that balance unattractive, and the sustained activity needed to support the model hasn’t materialised. • Important dependencies are built into the deployed contracts. Addressing them properly would require a substantial rebuild. • Liquidity is committed to the existing pool. I can’t simply withdraw it, move everyone to new contracts and carry on with the same economy. After reviewing the options and consulting more experienced developers, I don’t see a sustainable long-term path for this version through incremental updates alone. WHY NOT LAND? Land could have brought fresh activity and more uses for SHELL. But a token sink doesn’t remove the game’s underlying operating requirements. It would also add rewards and services to maintain. I don’t think launching another mint for temporary breathing room is the right decision while those problems remain. A different design could keep ownership and important financial guarantees on-chain while moving more routine gameplay off-chain. But that would be a different foundation, with different trust tradeoffs, not a simple upgrade. WHAT HAPPENS NEXT • The current game will receive another 30–60 days of support, as outlined in Discord. • I’ll share exact dates and instructions for outstanding trips, returns and claims before support ends. • I’m investigating whether a simpler idle mode could preserve some ongoing SHELL earning for eligible holders. That isn’t confirmed, and I won’t promise it until I know what can reliably be maintained. I put a lot into trying to make this work, and I know everyone who backed it put their own time, money and trust into it too. Thank you to everyone who tested, played, reported bugs and built a flock. I wanted to take this further and it's truly upsetting to me having to end it on this note. My focus now is on supporting the transition and being clear about what comes next.
2
1
11
943
Mr.Matching retweeted
Starting an X group for V4 hook szn 🦄🪝☀️ This isn’t tied to any specific project, it’s for everything V4 hook related. V4 hook szn is going to make AI agent szn 2024 look tiny. So many unique V4 hook tokens and we’ve barely scratched the surface. xitter.cf/i/chat/group_join/g209…
28
4
6
77
11,290
Mr.Matching retweeted
ok nice
20
5
5
270
29,165
Mr.Matching retweeted
Replying to @viperr
Sorry kiddo it’s just business
154
63
38
1,722
176,705
Mr.Matching retweeted
i thought the chain was immutable, not the price 17 august 2022: 1 ETH = $1,880 9 november 2023: 1 ETH = $1,880 16 aug 2026: 1 ETH = $1,880 incredible technology
101
128
25
1,854
227,496
Mr.Matching retweeted
Pick your path carefully 🗺
14
27
46
3,555
Mr.Matching retweeted
69
14
2
524
41,478
Mr.Matching retweeted
This Uniswap V4 hook launches tomorrow at 11am ET. First coin launch to gate users on PvP. Huge possibilities for gamified token launches after this lands. Reach out if you’re a game dev. xitter.cf/flaunchgg/status/20846…
The design space for Uniswap V4 hooks is... broad. Swap validation with a bow and arrow 🏹
20
9
5
134
30,278
Mr.Matching retweeted
the smartest people you know type to agents in the most broken english imaginable
104
70
31
1,772
84,619
Mr.Matching retweeted
my ideal AI interface is a single never-ending chat thread. i don't want to think about the concepts of sessions, context windows, worktrees, mcp servers or really anything else. The harness should automate everything transparently.
190
64
54
1,701
192,359
Mr.Matching retweeted
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.
2,083
5,826
3,205
56,106
21,838,903
Mr.Matching retweeted
I just open sourced Siftly, a self-hosted AI knowledge base for your X bookmarks. Most people save thousands of tweets and never use or find them again. Siftly fixes that with a full AI pipeline that runs locally on your machine. Here's what it does:
120
84
11
1,439
105,190
Mr.Matching retweeted
Today Unity announced they'll demo "prompting full casual games into existence" at GDC next month. This is the most important announcement in gaming this year and nobody in the industry understands why. It's not important because it will work. It's important because it confirms that the largest game engine company on earth looked at the future and saw exactly what we saw, and their response tells you everything about why gaming is about to break wide open. Let me explain. Gaming is the largest entertainment industry in the world. Bigger than movies and music combined, then doubled. And it is structurally failing. Not financially, the money is still there. Structurally. The architecture of how games get made, distributed, and consumed is broken at every layer, and the people running it have no idea how to fix it. Start with the engines. Unity and Unreal were built for human developers writing C# and C++. Every line of their architecture assumes a person is sitting in an editor, dragging assets, writing scripts, compiling builds. Retrofitting AI onto that is like bolting a jet engine onto a horse-drawn carriage. The frame wasn't built for that speed. It will shake apart. Unity's announcement today is exactly this. They're not showing a new engine built for AI. They're showing AI bolted onto the same engine that caused the runtime fee disaster two years ago. They're promising "prompt full casual games" but the underlying architecture still assumes someone will eventually open the editor and write code to make it real. It's a demo, not a product. Now look at distribution. Steam actively restricts AI-generated content. Apple is cautious about it. The major storefronts, the places where games actually reach players, are building walls against the future instead of roads toward it. This isn't temporary. These are institutional antibodies rejecting what's coming. Then look at the people. This is the part nobody wants to say out loud. Game developers are the most vocally anti-AI creative workforce on earth. Concept artists, writers, animators. They've turned AI resistance into a cultural identity. This isn't like software engineering where devs adopted Cursor and Copilot and shipped faster. Gaming has made opposition to AI a moral position. Which means the studios can't respond even if they want to. A creative director at Ubisoft can't walk into a room and say "we're replacing half the art pipeline with AI" without a revolt. The org won't let them. The talent won't let them. The culture won't let them. The entire industry's workforce has self-selected against the technological shift that will define the next decade of thier field. You can rewrite an engine. You can't rewrite a culture. Every other creative medium already went through its democratization moment. Publishing had blogs. Video had YouTube. Music had GarageBand and then TikTok. In every case, the old guard said the tools would produce garbage, the quality would drop, the professionals would be replaced by amateurs. And in every case, what actually happened was an explosion. Not of garbage, but of volume. And inside that volume, the best stuff was better than anything the old system could produce, because the talent pool went from thousands to millions. Gaming never had that moment. The barrier stayed high. The tools stayed professional-grade. The industry calcified around $200M budgets, 5-year dev cycles, and games designed by committee to extract maximum revenue per user. And we got a decade of live service slop. Meanwhile the best games people actually love - Stardew Valley, Terraria, Minecraft, Celeste, Hollow Knight, Undertale - were all made by 1-5 people with vision and taste. The industry went one direction. The players went the other. That gap is the opporunity. Now look at what's actually happening on Spawn today. A user who cannot write code built a full soulslike action RPG this week. Class selection. Combo trees. Boss fog gates. A "YOU DIED" screen. Leveling, checkpoints, loot. Another user built a networked MMO zone in a day and a half. Target-based combat, quests, XP, abilities, multiplayer physics. On the side of his day job. These aren't demos. These aren't cherrypicked screenshots from an internal team. These are real people, building real games, right now, with no code and no engine license and no team. Unity is announcing a demo for March. Our users already shipped. The reason gaming is about to break open isn't because AI got good enough to make games. It's because gaming is the last creative medium where the tools haven't caught up to the talent. There are millions of people who grew up playing games, who have incredible taste, who know exactly what they want to build and couldn't. The barrier was always technical, never creative. That barrier is gone now. Taste is the new literacy. Go build somthing.
80
50
26
531
56,624
Mr.Matching retweeted
cigoL: agentic infrastructure for prediction markets. Deploy agents that do multi-turn web research, analyze odds, execute trades, and learn from outcomes. Not a vault. Not signals. Not a static bot. It’s adaptive tooling you configure and improve. t.me/cigoLdeployerbot?start=…
24
2
3
56
17,363
Mr.Matching retweeted
Crypto’s BIGGEST Advisors are joining the Pump fun BiP Hackathon! Now is your chance to access the most successful & biggest thinkers in crypto & beyond, as well as the chance to receive a part of the $3M investment from Pump Fund, regardless of your stage Meet the Advisors 👇
769
243
141
1,853
618,476
Mr.Matching retweeted
Congrats to our vibeathon winners Net new products: 🏆 @nomos_protocol Nomos, a Decentralized resolution protocol Watch: xitter.cf/nomos_protocol/status/… 🥈 @Back2Matching Ethos Pad, a fair launchpad using Ethos scores Watch: loom.com/share/e7bdf7c7669c4… Reputation driven improvements: 🏆 @dethective Telegram Noise Canceler - Telegram feed aggregator + telegram caller performance Watch: loom.com/share/026f453883c84… 🥈 @Magicianafk Ethos pocket, credibility scores on X mobile Watch: loom.com/share/b1af2fe4b2424…
32
12
11
147
16,543
Mr.Matching retweeted
On the recent discourse within PMs on bots/algorithms taking over Prediction Market volume, Do you think this will have a positive or negative effect?
79%Good thing
21%Bad thing
47 votes • Final results
7
2
1
16
3,464
Mr.Matching retweeted
Can automated agents make money on @Polymarket? Benchmark #5 now live with 24 cigoL agents across 4 profiles trading real money 24/7. Currently the leaders are cigoL Skeptic and cigoL Trend as we pace towards ~24 hours running. Live: cigol.ai
3
1
12
1,470
Mr.Matching retweeted
[Incident Update] Going into Benchmark #3 around ~2 days earlier then planned, featuring several updates to agents and fixed some core issues that ruined current benchmark analytics. We encountered a critical issue where GPT-5 re-entered the same position 8 times during an API disconnection. Fixes deployed, and monitoring tightened to avoid this in future. [System Progress] Week 2 agents with improved profiles significantly outperformed week #1 stats. Reaching over 10x+ better volume to pnl ratio vs last week, and that's including the gpt-5 error that set us back ~$500+ Gemini’s last trade just printed ~10x in ~3 hours, posted with 95% confidence making it the winner this week taking the lead from deepseek at final moments. [Migration] Final timing for the Base relaunch is being confirmed. Updates will post on TG and X. Live: cigol.ai/ TG: t.me/cigolportal
2
1
12
989