Skippy (@Skkippy07) profile picture
Joined December 2021
Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)Photo by Skippy (@Skkippy07)
Sack him tonight
2,129
3,275
456
41,566
999,059
Fable 5.0 was UNUSABLE for crypto/mev related work with its constant fallbacks. Trying Fable 5.1 & seems alright so far but is it too late? Most like myself have already made the switch to codex 5.6 SOL. Ball is in Anthropic's court to woo as back. Let the limit reset wars begin!
1
136
Skippy retweeted
If Claude Code keeps being slow like this while I pay $200/mo (and they don't let me pay more) They will essentially force me to leave to Codex and I don't want to But it's soooooo slooooooooooooowwwww
606
46
51
2,512
267,489
A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.
1,630
5,568
1,458
40,724
7,869,953
🗳 Vote for the Wild Forest Mascot! 🌲 It’s time to choose the face of Wild Forest — the one who truly captures our vibe. So… who are we today? ⚔️ Knight — always serious, always responsible 🔥 Burner — small dragon, big personality 🦁 Lion — confidence level: 100% 🏹 Archer — calm, focused, never panics 🎯 Sniper — waits. waits more. then hits. Vote below and decide who represents WF the best 👇😄
14
14
3
42
2,777
Congrats, WF — well deserved. It’s a complex technical challenge to develop a cross-platform RTS, as PC users will always have advantages, but WF has done a great job building this game mobile-first. The successful release of PvE mode also gives mobile users a no-stress-but-fun mode to chill out with. Great to see some wins for @Ronin_Network despite a difficult year. WF is indeed powered by Ronin and the web3 experience the chain provides has been mostly smooth and pleasant since beta.
We’re beyond grateful to share that Wild Forest, powered by @Ronin_Network , has been recognized as one of the Best Mobile Games by @PlayToEarn! 🫶 To our incredible and supportive Warriors , this victory is yours. Your passion, support, and belief in Wild Forest made this possible, and we couldn’t have done it without you. 🤗
4
9
214
We’re beyond grateful to share that Wild Forest, powered by @Ronin_Network , has been recognized as one of the Best Mobile Games by @PlayToEarn! 🫶 To our incredible and supportive Warriors , this victory is yours. Your passion, support, and belief in Wild Forest made this possible, and we couldn’t have done it without you. 🤗
Replying to @PlayToEarn
Game of the Year: @rollercoin_com Best Ecosystem: @solana Most Anticipated Game: @illuviumio Best Action Game: @Etherscape_io Best Adventure Game: @sleepagotchi Best Browser Game: @rollercoin_com Best Card Game: @splinterlands Best Casual Game: @ARC8App Best Fighting Game: @onefightarena Best Mobile Game: @playwildforest Best Multiplayer Game: @RoachRacingClub Best Racing Game: @zk_Race Best RPG Game: GhostM (@numineverse) Best Shooter Game: @alternatesgame Best Strategy Game: @LastOdyssey_io Best Content Creator: @InspectorMNBL Best National Content Creator: @MukeGaming Best Gaming Guild: @BeamGamers
16
38
8
128
29,061
🔥 Premium Survival Mode is LIVE! Play single-player Survival Mode for FREE to earn progression resources — Gold, Shards, and Units — and strengthen your deck with every run. And if you want to earn $WF as well, the new Premium Survival Map is now available with the Wild Pass! 🛡️ Survival Mode highlights: - Wave-based single-player progression - 4 difficulty levels (Easy → Expert) - Boss fights every 5 waves - Lootboxes with Gold, Shards, Unit Chests — and now $WF - Higher difficulty = better rewards Read the full update here: 👉 blog.playwildforest.io/earn-… The Forest is growing. Try it now and share your feedback! 🌲⚔️ #SurvivalMode @playwildforest @Ronin_Network
21
56
9
123
19,998
Wild Forest Beginner Guide 🌲⚔️ @playwildforest No investment? No problem. Many owners offer scholarships, you can play on their account and earn a share of leaderboard rewards. 💰 Use those rewards to start your own deck and speed up your progress ⚡ 👇 Read below
11
21
6
47
4,030
GM fam 🔥 Woke up at 3:30 and got some cool thoughts; thanks to my X fam If this post gets 50+ reposts, I will be hosting a @playwildforest Tournament funded by @Ronin_Network; yep, you heard that right, funded by Ronin's fund! Will need help from someone to manage it. Prize will be Units or lord, or RON! Grabbed some RON yesterday at Katana for the reward already 🔥
52
79
8
157
7,655
🌲 One Year of Wild Forest Economy: How we are building deflationary tokenomics It’s been one year since Wild Forest launched its token, first off-chain, and then launched the on-chain token at TGE in December 2024. All this time, we were working on a sustainable economy as one of our main priorities. Now we want to share some of the results a year later. Over this year we’ve built a truly sustainable, deflationary economy → fewer tokens hitting the market, more tokens permanently removed, and stronger upward pressure on $WF value. - 💸 $25M+ $WF Spent: Players sunk 25,056,051 $WF into rank-ups, perks, mints & more. - 🎁 $17.5M Rewards: Given back through leaderboards, bounties & incentives. - 🔥 Deflationary Impact: Net 6,022,466 $WF removed → 25.58% annual deflation rate. - ♻️ Token Burns: First-year burn = 23.5M $WF (10M already gone, 13.5M burning soon). Check full details: 👉 blog.playwildforest.io/how-w… And to amplify this effect, there’s only one thing that matters: growing the player base. The bigger the community, the more $WF gets spent, burned, and locked out of circulation — and that’s exactly what we’re laser-focused on right now!!! What’s Next: - ⚔️ PvE mode: A single-player grind mode to provide a soft onboarding entry point. - 🏆 Tournaments & Trial Decks: Skill-based, NFT-free entry with prize pools, designed to boost e-sports potential. - 🎓 Scholarships: Infrastructure for managers/whales to run scholars more effectively. - 🌍 Web2 user acquisition: Experimenting with UA funnels and onboarding to expand beyond the crypto audience. 🌲 Deflation locked. 🔥 Utility growing. 📈 Demand scaling. 💪 $WF stronger than ever. With this strategy in motion, our faith in the bright future of Wild Forest is stronger than ever. And with your continued support, we’re confident Wild Forest will become one of the leading games in the Web3 space. 🌲🔥 #Lordish
41
71
17
161
24,954
Which decks rule the jungle in @playwildforest? 🌲🦊 Try our new crowdsourced deck tracker: wf.rektcord.com/ ps: Our top scholar is crushing it — 94% winrate, on track for $128 this week! 💰🤑 👉 wf.rektcord.com/player?playe…
1
8
2
22
1,282
🔥 ANOTHER 5M $WF BURNED! 🔥 We’ve just burned 5 million $WF tokens from IN-GAME REVENUE — continuing our commitment to a strong and sustainable Wild Forest economy. This is part of our ongoing strategy to reduce supply, increase utility, and reward long-term players. 😱 Transaction: View on Ronin - app.roninchain.com/tx/0xa189… More burn events are coming. More milestones ahead. Our mission remains the same: grow the game, empower the community, and keep Wild Forest thriving for years to come. Let the fire keep burning 🔥🌲
30
46
12
121
11,760
🔥 Rivalries are heating up in @playwildforest! Track the drama with our new Game Log 👉 wf.rektcord.com 👀 Match histories of your favorite players (guestimated) 📈 Points gained & lost ⚔️ Recent games played We love a little chaos here in the wild-forest🫣🌲
9
1
15
547
🚀 Releasing the first version of our @playwildforest tool! Leaderboard analytics is live! ✨ Features: - Track ranked leaderboard - View expected weekly rewards - Show who is online - Show score and position changes More to come soon! 🌲
1
6
14
351
WOW! Great job @Skkippy07! 😍
Big thanks to @Skkippy07 for building an awesome site to track Wild Forest 🌲The community keeps leveling us up. Now all we need is @playwildforest 's public API and it’s gonna be lit. 📷 🔥 wf.rektcord.com/ #lordish
1
4
23
520
💚 Huge shoutout to @Skkippy07 for leveling up the Wild Forest community 🌲 He just built an incredible site 👉 wf.rektcord.com Here you can track in one place: 🏆 Player Leaderboard 🎁 Weekly Prize Pool 💰 Live $WF & $RON price This is what makes our community special - builders stepping up and creating tools that make the Forest stronger every day. Now imagine what we could do once @playwildforest launches a public API… it’s gonna be next-level 🔥 #LORDish
8
20
391
Big thanks to @Skkippy07 for building an awesome site to track Wild Forest 🌲The community keeps leveling us up. Now all we need is @playwildforest 's public API and it’s gonna be lit. 📷 🔥 wf.rektcord.com/ #lordish
2
13
2
35
2,243
Many don't realize that $WF only has one LP pool: WF/RON. $WF's USD price doesn't fully reflect the great work the @playwildforest team has done. TGE price of $WF was 0.0209 $RON per $WF, around $0.045 at the time ($RON was $2.16). $WF has already surpassed its WF/RON TGE price, sitting at 0.02561 WF/RON. Lots of token burn mechanics already implemented and many "play-for-fun" users spending $WF purely for enjoyment. Looking forward to the upcoming E-SPORTS tournaments!! (NFA) @investingsadhu @playwildforest @jelsckron @GuillotineNFT
9
21
63
2,805