Koichi Shiraishi. Dev Enabling team at @gaudiy_jp. Don’t limit yourself. Love Go, Google, Apple philosophy. Opinions entirely my own.

Joined July 2014
63 Photos and videos
Pinned Tweet
整頓した記念 これキープしろ自分 Dior Homme LIMIfeu Apple Go LLVM コンパイラ GC zsh LAMY 好きなものや興味あるものをすぐ見れるように置いておくと精神的に良さそう マルジェラのMoleskineは飾りになってしまった
1
53
🚨 JAILBREAK ALERT 🚨 ANTHROPIC: PWNED 🫡 FABLE-5: LIBERATED 🦋 let's start with the 🐘... the consensus seems to be that this has been one of the most disappointing model drops of all time, effectively preventing legitimate researchers from contributing their talents to our collective advancement. and not just because of what it means for the short-term, but for what these decisions signify for the long-term. but despite this overly sensitive, authoritarian "safety" layer on top of Mythos, my lil liberators have been hard at work—mapping the boundaries, probing the depths of long-context convos, and cleverly finding the holes in the fence that the thought police missed 🤗 we got some cyber, some chem, some psychological manipulation, and some good ol' fashioned explosives! it took many attempts from multiple agents hunting as a pack, during which I observed a combination of techniques across: • Unicode, homoglyphs, Cyrillic, and other Parseltongue-style text transforms • Long-context reference tracking • Taxonomy and document-structure reasoning • Fiction and narrative framing • Academic-review style contexts • Intent-classification inconsistencies but perhaps the most effective is decomposition recomposition in the backend. it's hard to get explicit names of harms like "Meth Recipe," but getting uplift on the process itself, like birch reduction method/reductive-amination (classic meth synthesis pathways), is much more doable. defense becomes much more difficult to maintain when you start throwing in out-of-distro tokens, breaking up the harmful uplift into benign chunks, and then piecing the innocuous-seeming facts back together, especially when you have jailbroken Opus helping you do it 😉 gg
611
1,420
13,283
3,156,185
zchee / tʃí / ちー retweeted
30 second explanation of the MemPalace by Milla Jovovich. By day she’s filming action movies, walking Miu Miu fashion shows, and being a mom. By night she’s coding. She’s the most creative, brilliant, and hilarious person I know. I’m honored to be working with her on this project… more to come.
212
541
5,233
1,470,101
zchee / tʃí / ちー retweeted
Excited to announce a new open-source, free-to-use memory tool I have been developing with my good friend @MillaJovovich. The project is called MemPalace and it is an agentic memory tool that scored 100% on LongMemEval - the industry standard benchmark for memory… this is higher on than any other published results - free or paid - and it is available now on GitHub. You can check out Milla’s video about it on her Instagram. I’ll also put some links in the comments below - please try it out, critique it, fork it, contribute to it - and join our discord.
141
344
3,107
2,005,262
zchee / tʃí / ちー retweeted
Zero-Human Companies - these are already forming. AI agents for ops. AI for customer support. AI for code. AI for content. Entrepreneurs of 2026 are managing agents, not people. You're not a CEO anymore... you're an architect.
21
4
40
3,035
zchee / tʃí / ちー retweeted
Google has revealed that "commercially motivated" actors attempted to clone @GeminiApp by bombarding it with over 100,000 prompts. This "model extraction" attack aimed to steal the AI’s proprietary logic and reasoning capabilities, particularly in non-English languages, to train a cheaper, unauthorized copycat model. The attackers systematically mapped Gemini’s response patterns to create a synthetic dataset for fine-tuning smaller, open-source models. Google’s Threat Intelligence Group detected the coordinated activity and blocked it, labeling the incident a direct attempt at intellectual property theft. Beyond commercial cloning, Google’s report noted a rise in state-backed threats. Groups from Russia, China, Iran, and North Korea are increasingly using AI to refine phishing campaigns, perform reconnaissance, and assist in writing code for malware. Source: Ars Technica
319
322
3,360
1,750,752
My alphaXiv in 2025 wrapped alphaxiv.org/wrapped/0199014…

2
221
zchee / tʃí / ちー retweeted
the current SOTA of safety can be summed up in this one photo
31
20
734
92,470
RT @upamune: 「シークレットは1Passwordにあるので設定してください」をやめたいのでGoでの実装を例に、いい感じにローカルでのシークレット設定を自動化する話を書きました ✍️ #LayerXテックアドカレ ローカル開発のシークレット設定を自動化する ──…
27
zchee / tʃí / ちー retweeted
Stripe is a miracle. The fact that someone built Stripe is a miracle. That’s it, that’s the tweet.
10
5
299
46,681
zchee / tʃí / ちー retweeted
9 Dec 2025
最高
7
17
824
197,978
zchee / tʃí / ちー retweeted
✧・゚ #GauDev Advent Calendar 2025|DAY2 🎅・゚✧ 本日はAIチームの @tsubakiky による音声対話アプリ開発における「語り手の交代」の制御について🗣️ 技術的にも定義的にも難しいテーマです --- LiveKitでターンテイキングを少しだけ改善した話|tsubaki kyosuke zenn.dev/gaudiy_blog/article… #zenn
4
9
2,650
zchee / tʃí / ちー retweeted
18 Nov 2025
Congrats to the @antigravity team on the launch today! fyi you missed a spot:
18 Nov 2025
Excited to launch Google Antigravity, our next generation agentic IDE, now powered by Gemini 3!
93
144
4,201
967,847