Daniel Lee (@dylayed) profile picture

개발 이야기를 좋아합니다.

San Francisco, CA
Joined September 2015
Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)Photo by Daniel Lee (@dylayed)
Oh my god it can sing in Korean too
my vocal synth models the vocal tract as a network of branching acoustic tubes, unlike vocaloid which stitches together and pitch-shifts phoneme recordings. still working on improving naturalness by tuning it against recordings of real singers, but I'm already impressed at how cool it sounds!
3
4
1
63
3,312
Daniel Lee retweeted
my vocal synth models the vocal tract as a network of branching acoustic tubes, unlike vocaloid which stitches together and pitch-shifts phoneme recordings. still working on improving naturalness by tuning it against recordings of real singers, but I'm already impressed at how cool it sounds!
I only make serious software
339
1,221
163
10,924
680,488
Stop forcing a 2,700-word prompt + 900ms frontier model to do a fine-tuned smaller model’s job. 💪 @AirbnbEng just fine-tuned @GoogleGemma 4 E2B on a single GPU with @vllm_project, to serve as a JEV-like classifier. The results are pretty solid: ⚡ 35ms median latency (85ms p99) 🎯 0.902 F1 (matches frontier models) 📉 ~1% of the cost at scale 🔗 Read the full deep dive on GLOWC + their @GoogleDeepMind Gemma 4 setup here: airbnb.tech/ai-ml/frontier-q…
17
52
2
428
23,082
Daniel Lee retweeted
The engineer who says no all the time is a real archetype among senior and staff engineers. Their role is to slow things down, to block the development of features that add complexity, and to ensure that as little code gets written as possible (since code is a liability).
28
16
11
451
39,904
Daniel Lee retweeted
check out my new article in the Anthropic eng blog. i talk about "dreaming" (offline compute) as a way to organize Claude's memory. it can correct mistakes, create memories, or build new representations. nitter.cf/AnthropicAI/status/211…
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…
52
54
9
613
34,364
Daniel Lee retweeted
I unironically agree with @bcherny’s take that “coding is solved, but bugs are not.” The deeper meaning is that you can in theory code *anything* now. You can burn infinite tokens refining and optimizing. Including optimizations that no one will care about 💀 With Vercel you can build a different kind of recursive improvement loop. You capture traces from production, you then optimize and course-correct based on how your software is being used IRL. This is not a new idea. The best engineers I’ve ever worked with never jumped into coding (now prompting) right away. You instrument the system, collect data, understand distributions, user journeys, and then put fingers on keyboard. You can ask your agent today to look at your traces!
145
26
18
609
50,302
Vercel Tracing is now GA on all plans. Starting with Next.js 16.5, new projects have it on by default. Search and inspect spans from the dashboard or the CLI. ▲ ~/ vercel traces search --status error vercel.com/changelog/vercel-…
14
14
8
203
61,165
Daniel Lee retweeted
Just rolled out remote agents in Antigravity so now you can just fire and forget anywhere. It’s been the way we’ve been working at Google for some time so excited for you all to give it a go! More to come tomorrow 👀
82
48
26
938
107,613
Daniel Lee retweeted
my entire career, i have been warning people to not trust Linux for local privileges. i have always considered the VM boundary to be the minimum security for untrusted code, and limited the permissions of the VM (via things like IAM) to the smallest amount, assuming that any compromise of the software will compromise the entire system it may turn out that the security work being poured in vulnerability discovery is the first time that we get to a ~"provable safe" Linux, in which -- suddenly -- running *containers* is actually very safe (and cheaper than microVMs) because we *know for certain* that local privilege escalation is not possible this would be a big, surprising change and i would need to update how i think about building software
we've found, validated, and prepared patches for almost 1,000 linux local privilege escalations using our cyber vulnerability pipeline, at the cost about $1,000 per vulnerability. an emerging scalable approach to significantly hardening both open source and proprietary projects
33
29
8
703
83,627
Daniel Lee retweeted
Our security researchers built an autonomous cyber vulnerability discovery, exploitation, and patching pipeline. In a single run with an upcoming cyber model, it validated and generated patches for 948 local privilege escalation vulnerabilities in the Linux kernel at a total API cost of $1.2 million.
679
1,339
907
12,813
2,280,438
Daniel Lee retweeted
Friday was my last day at Anthropic. Two years ago, when Claude Code was a small internal tool, I asked it to build an RL env. I steered it for tens of hours but never manually wrote a line of code. It worked, I was hooked, and I joined the team. When we first launched, most people approved every permission prompt by hand and mostly used Claude to answer questions and write tests.  Today, the default is trusting Claude's judgment to auto-approve. Claude does large migrations and builds new products.  Helping build Claude Code into an industry-defining product has been the journey of a lifetime.  Thank you to the incredible team behind Claude Code, Cowork, and Tag. These products are the sum of thousands of great ideas from you. I'll miss working with you all. Thank you to our users for embracing a new way of working. Your constant feedback shaped so much of what we shipped and your stories made the work so meaningful. Excited to see what you all make next!
1,228
534
563
16,648
4,676,724
Daniel Lee retweeted
wterm now supports WebMCP Agents can use the terminals on your page → List, read, type, press keys → Opt-in per terminal, read-only mode → React, Vue, Svelte + vanilla → No DOM scraping or fake key events Below: 5 fx agents launch each other across 4 browser terminals
50
41
15
420
84,310
Daniel Lee retweeted
Many software engineers are fatalistic about company politics.
37
40
9
1,034
211,381
Daniel Lee retweeted
Working with Gemini on fx.sh is hilarious 😂😂 Other than being SUPER EXCITED!, I've been testing it on two high complexity projects and it's doing great.
88
9
8
532
50,549
We are building AX to be a Kubernetes for agents to be able to manage other agents. Our assumption is workloads will be provisioned and managed primarily via other agents not by humans. Agentic loop is the new job controller loop.
37
23
5
356
35,408
Daniel Lee retweeted
no matter what agent you're using, your voice is the best way to talk to them and hex is the best way to use your voice: - fast - runs locally - works on mac, windows, linux stable release now available: anoma.ly/hex
401
467
318
9,176
1,142,403
Daniel Lee retweeted
you can now use your claude subscription in OpenCode
Replying to @claudeai
@claudeai subscriptions in @opencode are back! Check it out
434
421
369
8,726
1,154,961
Daniel Lee retweeted
Introducing agent-desktop agent-browser, for your whole computer → Computer Use for any coding agent → macOS, Windows and Linux → Runs in bg while you keep working → Agents use your computer in parallel, each with its own cursor
603
784
448
10,208
1,510,304
Daniel Lee retweeted
celld works really well such that even given how it is today i'm happy with it and don't need it to do much more and feel perfectly comfortable with maintaining it for my needs it'd be cool to see the private repo tokens @rough__sea has talked about, but i'm thankful for the project regardless ⭐️
Replying to @samgoodwin89
@joelhooks you're using this right? Have you seen anything troublesome?
3
2
26
2,328