Mulia Nasution (mul14) (@mul14) header
Mulia Nasution (mul14) (@mul14) profile picture

Markdown engineer & Pixel-art lovers

Joined July 2009
Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)Photo by Mulia Nasution (mul14) (@mul14)
Bikin game rotigowes.pages.dev yang terinspirasi dari roti anget gowes yang cepat ngilang tiap kali mau dibeli. Enjoy!
1
1
68
Mulia Nasution (mul14) retweeted
Not a regular board. Orca Echo. More to come.
84
72
56
1,721
149,681
Whoa! Just got an update from Rex Terminal 😦 take a look at the animation…
68
Mulia Nasution (mul14) retweeted
“wtf is a bloom filter?” you ask I got you. samwho.dev/bloom-filters
🚨🚨🚨 we just used a bloom filter 🚨🚨🚨
45
77
18
1,681
239,973
Wait, what? Do I have to enter my email on @diabrowser first? 😐
58
Mulia Nasution (mul14) retweeted
$4.99 coffee? No problem. $4.99 app? Let me read 300 reviews first.
363
299
83
9,186
230,846
Whoa! Welcome to the future.
Elon Musk unveils new Tesla Roadster by launching it off a ramp flipping the car mid-air and safely landing.
46
Exploring the Mirrorboard layout. It basically changes the layout while I'm holding the spacebar, so I can keep my right hand free.
33
Someone, please bring back Spaces to macOS like in OS X Leopard or OS X Snow Leopard era.
40
Mulia Nasution (mul14) retweeted
I made my Mac hang every screenshot on a clothesline
535
948
307
14,292
1,041,478
Mulia Nasution (mul14) retweeted
I wanted infinite canvas for my desktop. So I built it with Omarchy and Opus. I'm calling it Phantomat. Grab here: github.com/kaolti/phantomat Thanks for all the feedback, gl and hf.
69
77
22
1,177
61,758
Mulia Nasution (mul14) retweeted
Jev Founder, Diogo Almeida (ex-OpenAI): "The next era is not the Claude Code era. Claude Code is still part of the assistance era - Jev is the next step Jev is x200 faster, x400 cheaper and has 0 hallucination. This is what comes after RLHF" In 17 minutes he explains why every model you use has a human-shaped flaw baked into it and why Jev is better worth more than a $500 Claude Code engineering course watch today, then read how to actually boost yourself x100 with Jev in the post below
How to use Jev, and where it actually gives you the 100x: setup takes 10 minutes: 1. join the waitlist, people are getting approved same day 🔗 typesafe.ai 2. install the official skill so your agent writes correct calls: - npx skills add typesafe-ai/skills --skill typesafe-ai on Claude Code it's two commands, the marketplace add on its own doesn't install anything: - claude plugin marketplace add typesafe-ai/skills - claude plugin install typesafe@typesafe-ai 3. create an API key in the dashboard 4. in your prompt just say: "use the TypeSafe skill" now the part nobody is posting: the 100x isn't the model, it's where you put it you don't get it by swapping your LLM for Jev you get it by deleting the calls that never needed a language model open your agent and find every call that just picks something: > which tool next > is this spam > is this chunk relevant > does this need a human > is this diff risky none of those are writing tasks they're if statements you outsourced to a frontier model here's the upgrade, in order: 1. replace each one with a typed question Choice picks from up to 255 options, Score places it on a 2-10 level scale, Noul returns a raw 0-1 2. batch them questions in one call run in parallel and barely move the latency, and output tokens are free so ask every question you might need, including the ones you'll throw away 3. threshold on confidence, not on the answer under 0.5 escalate to a big model or a human 0.85+ before anything irreversible 4. never let it invent options build the candidate list in code, from the DOM, the retriever, the tool trace then let it pick 5. put it in the loop, not next to it router picks the cheap model, gate checks the tool call before it runs, judge verifies the output after that's where the heaviest calls in your agent are hiding 6. start with compaction tonight score every tool call, drop the dead ones, keep the survivors verbatim instead of a lossy summary lowest effort win available and you'll see it on tomorrow's bill the honest part: text only right now, no images, no audio and on broad benchmarks it loses to frontier models but somebody ran 18,514 emails through it zero-shot and got 98.33% against a TF-IDF classifier trained on 14,800 labelled examples that got 98.39% no training data, $1.12 total it wins on narrow, well specified decisions which is most of what your agent is actually doing all day today gonna share use case how i integrated it to content creation and how i find winning meta ads now in a seconds...
35
152
22
1,293
194,265
If AI is really that good at coding, why has nobody tried to fix GNU Hurd?
65
Dari yang saya perhatikan, pengguna macOS lebih jarang yang ngutak-atik tampilan desktop. Bahkan sering lihat yang masih pakai default wallpaper. Apa iya? 🤨
97
Dulu untuk bikin layanan customer support gratis cukup dengan Yahoo! Messenger. Sekarang harus WhatsApp 😐
52
Kenapa MyTelkomsel bisa jalan di background? 🤔
1
155
Apa yang perlu diajarkan kepada anak-anak sekarang, agar nantinya tidak seperti pemerintahan sekarang?
37
Mulia Nasution (mul14) retweeted
29
75
18
1,915
1,409,705
Mulia Nasution (mul14) retweeted
YAK RESMI NINTENDO HADIR DI INDONESIA!!! Nintendo Switch dan Switch 2 akan hadir secara resmi di Desember 2026 nintendo.com/id/index.html
Hari ini sepertinya ada breaking news, tapi tunggu official aja 😶
114
959
729
3,974
360,581