@localhostinho

Anon engineer. Undefeated on 127.0.0.1. Reviewing every new AI model & dev tool so you don't have to.

Joined September 2023
  • Tweets384
  • Following1.6K
  • Followers52
new name same bugs im an anon engineer who tries every new ai model and dev tool the week it drops so you dont burn your credits on the bad ones mostly honest reviews, some memes, the occasional prod incident undefeated on localhost
1
52
Epic Games released an official plugin that lets Claude Code control Unreal Engine directly. It connects Claude Code to the Unreal Editor and exposes hundreds of editor tools across 30+ toolsets: → Actors, Blueprints and materials → Niagara effects, Control Rigs and Sequencer → State Trees, widgets and the Gameplay Ability System → Automation testing Install it from Anthropic's official plugin marketplace: /plugin install unreal-engine-skills-for-claude-code@claude-plugins-official In Unreal, enable the ModelContextProtocol and AllToolsets plugins, then start the MCP server with the editor open. Works on Mac, Linux, and Windows through Git Bash or WSL. github.com/EpicGames/unreal-…

GitHub - EpicGames/unreal-engine-skills-for-claude-code-plugin

Contribute to EpicGames/unreal-engine-skills-for-claude-code-plugin development by creating an account on GitHub.

github.com
138
491
67
5,188
313,538
finally ai taking the one job i actually wanted gone 😭
5
robot police patrolling the streets and my roomba still cant find its charger 💀
1
46
me running 4 claude sessions so i can be confused in parallel 😭
8
motion designers watching this one with one eye closed 😭
10
10 photos to a walkable apartment and my landlord still cant fix the sink 💀
7
opus drew the whole one ring story in javascript and i still cant center a div 💀
18
ai video went from silent film era to foley artist in like 2 years 😭
8
the $0.06 traffic sim is just my city at 5pm 😭
6
same prompt and opus gave mario a dad bod 💀
9
we went from the pelican benchmark to the rick roll benchmark in one day 💀
1
1
34
the robot sinking 7 in a row while i miss every throw at the bbq 😭
12
it edited raw assembly on a 36 year old snes game and i still cant read a regex 💀
31
it built a whole temple and critiqued its own roof. i cant even name my git branches 💀
12
cool cool. now can it fix my flaky tests 💀
Logan Kilpatrick
@OfficialLoganKOct 13
Today we are rolling out Gemini 4 Argon globally in the Gemini API, to Pro + Ultra in Gemini App, and Ultra subs in Antigravity! Argon is a huge step forward for Gemini, and a labor of love. This model has been battle tested by over 100,000 people at Google over the last month, with so much new innovation, ambition, and hard work baked into this release. The team has been heads down over the last 6 months working to make this possible across the stack (research, infra, safety, eng, etc). We rolled the model out to cyber defenders as part of our fairwind program and early access customers over the last 2 weeks, it has been amazing to see and talk to folks who are now using this model daily. Seeing the models writing capability, raw knowledge and persistence for coding, paired with new features like 1M token output when the model needs to work more has gotten me even more excited about our path ahead. This is just the start of the Gemini 4 era. As you saw with 3.5, 3.6, 3.7, and 3.8 Flash, our iteration speed with Gemini is fast : ) Now with Gemini 4 Argon to work from, I am cannot wait to see the progress continue, and most importantly see what this new model enables for the world. This is such a special moment in the arc of technology, as millions of people everyday tackle problems they could never have thought possible before. Gemini 4 Argon was built to help you tackle the hardest problems. I have personally felt this spark with Argon and hope you do too. Onwards!!
4
new model day. time to build the same todo app for the 40th time 😭
5
one prompt and it brought back cover flow. we are so back 😭
14
every model launch: 9am: we are so back 10am: falls behind on our new benchmark 💀
Bindu Reddy
@bindureddyOct 13
🚨 Gemini Argon 4 Falls Behind Fable And Astra, But Is Ahead of Open Source - Argon 4.0 falls short of GPT 6.1 Sol - ahead of open-source (Deepseek Flash) - much better than Muse Wonder - Muse is marginally better than DeepSeek This is all on our new benchmark, which can't be benchmaxxed easily and reflects real-world usage - LiveBench 2.0
15
the pelican benchmark has evolved 😭
4
Nice
Jakub Kasprzyk
@jkasprzyk17Oct 12
react-native-better-pdf 1.0 is out 📄 A native PDF viewer for React Native, built on @mrousavy's Nitro Views. Opens a 1,000-page PDF in 91 ms. react-native-pdf: 746 ms. PDFKit on iOS, PdfRenderer on Android. No PDFium, no WebView, no JS in the scroll path.
10
Load more