Jason Frisch

3.2K posts

Jason Frisch

Jason Frisch

@jmfrisch

使えるねっと株式会社 代表取締役社長 CEO of Tsukaeru cloud services group Japan , Australia, Indonesia, US and Denmark

Nagano Katılım Aralık 2009
553 Takip Edilen290 Takipçiler
Jason Frisch
Jason Frisch@jmfrisch·
@PrisonPlanet Plenty of masks still in Japan.. they haven't managed to update their brains yet.
English
5
0
2
5.7K
Paul Joseph Watson
Paul Joseph Watson@PrisonPlanet·
Airport departure lounge. 2026 and they’re still out there, like Japanese soldiers still fighting the war.
Paul Joseph Watson tweet media
English
316
673
13.6K
496.2K
Jason Frisch
Jason Frisch@jmfrisch·
@dhh How do you separate Kimi and Claude usage?
English
0
0
0
957
DHH
DHH@dhh·
Dev bliss: Neovim in the center flanked by Kimi and Claude. Gotta love that TUI life 😍
DHH tweet media
English
76
29
1.3K
76.2K
Jason Frisch retweetledi
ClaudeDevs
ClaudeDevs@ClaudeDevs·
New in Claude Code: /ultrareview (research preview) runs a fleet of bug-hunting agents in the cloud. Findings land in the CLI or Desktop automatically. Run it before merging critical changes—auth, data migrations, etc. Pro and Max users get 3 free reviews through 5/5.
English
546
1.2K
16.7K
2.6M
Jason Frisch retweetledi
DHH
DHH@dhh·
@levelsio It's really bad in Denmark too. The degrowth/net-zero nonsense has sunk into the unconsciousness to a degree where they don't even notice or question the insanity. Like laughing gas being discouraged for births because of CO2 impact??? dr.dk/nyheder/indlan…
English
17
10
386
16.8K
Jason Frisch retweetledi
Handre
Handre@Handre·
Japan spent 30 years throwing everything at economic stagnation: zero interest rates since 1999, endless stimulus packages totaling over $6 trillion, quantitative easing that ballooned their central bank balance sheet to 130% of GDP. The result? Three decades of economic flatline. Austrian economic theory predicted this perfectly. You can't print prosperity. Capital misallocation from artificially low rates creates zombie companies that should have failed. Government spending crowds out productive private investment. Japan's politicians kept doing more of what caused the problem. The lesson stares every central banker in the face: stimulus doesn't create wealth, it redistributes and destroys it. Yet they keep reaching for the same broken tools.
Handre tweet media
English
81
360
1.4K
92K
Jason Frisch
Jason Frisch@jmfrisch·
@steipete I switched to Codex, and to be honest, I've never seen openclaw follow instructions so easily. It seems to have suddenly remembered all I trained it on when I first started. All bow to OpenAI!
English
1
0
1
235
Peter Steinberger 🦞
Peter Steinberger 🦞@steipete·
Anthropic now blocks first-party harness use too 👀 claude -p --append-system-prompt 'A personal assistant running inside OpenClaw.' 'is clawd here?' → 400 Third-party apps now draw from your extra usage, not your plan limits. So yeah: bring your own coin 🪙🦞
English
487
282
5.5K
1.6M
Jason Frisch retweetledi
使えるねっと
使えるねっと@Tsukaerunet·
【最新記事】 #SaaS とは?意味や仕組み、#クラウド との違い、代表的なサービス例、導入時のポイントまでをわかりやすく解説。#データ保護 や #バックアップ など、SaaS活用に必要な #セキュリティ 対策についても紹介しています。 tsukaeru.net/blog/understan… #dx #業務効率化 #情報システム
使えるねっと tweet media
日本語
1
1
1
128
Nainsi Dwivedi
Nainsi Dwivedi@NainsiDwiv50980·
🚨Breaking: An Anthropic engineer (@trq212) just broke down how they actually use skills inside Claude Code — and it’s a completely different mindset. Here’s the real system 👇 Skills are NOT text files. They are modular systems the agent can explore and execute. Each skill can include: reference knowledge (APIs, libraries) executable scripts datasets & queries workflows & automation → The agent doesn’t just read… it uses them The best teams don’t create random skills. They design them into clear categories: • Knowledge skills → teach APIs, CLIs, systems • Verification skills → test flows, assert correctness • Data skills → fetch, analyze, compare signals • Automation skills → run repeatable workflows • Scaffolding → generate structured code • Review systems → enforce quality & standards • CI/CD → deploy, monitor, rollback • Runbooks → debug real production issues • Infra ops → manage systems safely → Each skill has a single responsibility The biggest unlock is verification Most people stop at generation. Top teams build systems that: simulate real usage run assertions check logs & outputs → This is what makes agents reliable Great skills are not static. They evolve. They capture: edge cases failures “gotchas” → Every mistake becomes part of the system Another thing most people miss: Skills are folders, not files. This allows: progressive disclosure structured context better reasoning → The filesystem becomes part of the agent’s brain And the biggest mistake? Trying to control everything. Rigid prompts. Micromanagement. Over-constraints. Instead: provide structure give high-signal context allow flexibility → Let the agent adapt to the problem The best teams treat skills like internal products: Reusable. Composable. Shareable across the org. That’s how you scale agents. Not with better prompts. But with better systems. Save this. This is how AI actually gets useful.
Nainsi Dwivedi tweet media
English
22
87
401
38.5K
Globe Eye News
Globe Eye News@GlobeEyeNews·
BREAKING: Iran announces the Strait of Hormuz is open to all countries except the United States, Israel, and their allies.
Globe Eye News tweet mediaGlobe Eye News tweet media
English
3.3K
35K
272.2K
13M
Jason Frisch retweetledi
Sukh Sroay
Sukh Sroay@sukh_saroy·
🚨BREAKING: If you've used ChatGPT for writing or brainstorming in the last 6 months, your creative ability may already be permanently damaged. A controlled experiment just proved the effect doesn't reverse when you stop using it. 3,302 creative ideas. 61 people. 30 days of tracking. Researchers split students into two groups. Half used ChatGPT for creative tasks. Half worked alone. For five days, the ChatGPT group outperformed on every metric. Higher scores. More ideas. Better output. AI was making them better. Then day 7. ChatGPT removed. Every creativity gain vanished overnight. Crashed to baseline. Zero lasting improvement. But that's not the bad part. ChatGPT users' ideas became increasingly identical to each other over time. Same content. Same structure. Same phrasing. The researchers called it homogenization. Everyone using ChatGPT started producing the same ideas wearing different clothes. When ChatGPT was removed, the creativity boost disappeared -- but the homogenization stayed. 30 days later, same result. Their creative range had been permanently compressed. Five days of use. Permanent damage 30 days later. A separate trial confirmed it. 120 students. 45-day surprise test. ChatGPT users scored 57.5%. Traditional learners scored 68.5%. AI reduces cognitive effort. Less effort means weaker encoding. Weaker encoding means less creative raw material. You're not renting a productivity boost. You're financing it with your originality. The interest rate is permanent.
Sukh Sroay tweet media
English
882
3.9K
15.1K
3.3M
Jason Frisch retweetledi
使えるねっと
使えるねっと@Tsukaerunet·
【最新記事】 災害+サイバー攻撃に備える #BCP対策。特にITやクラウドへの依存度が高い #中小企業 にとって、BCP(#事業継続 計画)は「いつか」ではなく「今」考えるべきテーマです。#クラウド で始める5ステップを解説しました。 tsukaeru.net/blog/business-… #バックアップ #ストレージ
使えるねっと tweet media
日本語
0
1
1
88
Jason Frisch retweetledi
使えるねっと
使えるねっと@Tsukaerunet·
【最新記事】 日本リージョンでも海外法の影響を受ける可能性がある理由とは? CLOUD Actの基本・誤解・対策をコンパクトに整理。実務判断に役立つ要点を解説。 tsukaeru.net/blog/what-is-c… #クラウド #データ保護 #リスク管理 #クラウド法 #情報セキュリティ
使えるねっと tweet media
日本語
0
1
0
65