Phawin (@Lifez) profile picture

Software Engineer

Bangkok
Joined December 2008
Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)Photo by Phawin (@Lifez)
Phawin retweeted
Hey @culpium members. It's my pleasure to offer Culpium Executive members one of the first exclusive privileges of a founder-level subscription. Details inside my next article, tomorrow. Culpium Executive offers exclusive access & other perks Sign up now: culpium.com/subscribe
3
1
1
1,685
Canceling 8 x ChatGPT 500 subs w/@OpenAI. If you value your time, then OpenAI just isn't it right now. Poor service availability, and inference is super, super slow. This isn't even about model quality; the problems go far beyond that. @claudeai is 100/100 better choice right now, faster inferencing, better availability and the models are better too.
alright, i'm over openai. switching 95% to anthropic. seriously can't recommend openai right now. every time a reset happens openai turns to potato and falls over.
63
11
11
364
24,426
We're starting to see some agentic Rust forks (or alternative implementations) focused on iteration speed. More-so than the specific projects, I'm interested in the ideas being explored (and how they could evolve upstream), so wanted to collate a few here...
32
26
7
439
60,176
Introducing tsrs: a Rust port of the TypeScript compiler 🦀 We are not forking TypeScript! ◆ In close collaborating with the TypeScript team ◆ Up to 8x faster than TS 7.0 & ~70% less memory ◆ Runs in WASM, so it works in your browser & on Workers ◆ Soon part of the Oxc toolchain npx tsrs blog.cloudflare.com/typescri…
148
541
225
5,083
671,762
Phawin retweeted
I think... I might cancel Codex sub for the first time ever
151
21
7
1,034
56,794
Phawin retweeted
how do you trust your agents' work more? copy this post/link and give it to your @bot or agent! 1. codebase improvements: this is just good software engineering - better architecture, stronger types and invariants, clear boundaries. agents love to copy what exists and take the shortest path, so make the easy thing the right thing. categorically eliminate problems through code and you won't need to think about it again. 2. static analysis: lint rules, tests, CI, verification (eg TLA+). very token efficient ways to catch issues ahead of time. 3. prose: comments, rules, AGENTS.md, skills - anything that can't be enforced and requires agent judgment. use it minimally, but do use /create-verification-skill. 4. human review: the hardest to scale. at the rate agents land code, it's pretty much impossible to thoroughly review every PR, so spend that effort on the highest leverage point, designing an environment where agents do the right thing by default. this forms an inverse pyramid: you want most of your effort at the top, least at the bottom. codebase improvements are deterministic, making it more token efficient, and lets you sleep more soundly at night. install github.com/cursor/plugins/tr… and create a new Project: 1. look through my slack/chat messages and code review comments where i've given feedback on PRs, code, architecture 2. use /recall on my past transcripts to learn how i steer agents 3. /poteto-mode use /correct and /architect on past commits to find the most common pitfalls agents fall into, then propose a plan to rearchitect the code i own so it's more agent friendly. answer open questions with prototyping rather than defer to me, and back the plan with real data. 4. before you begin, use /sharpen + /in-your-own-words and confirm this prompt with me
610
526
123
7,010
774,803
AI made Spotify engineers faster at shipping code. But it also exposed a new problem: keeping quality under control at that speed. Spotify shares what it learned the hard way, from production incidents and code churn to testing, mobile quality, and infrastructure pressure. The lesson for every engineering team building with AI: Generating code faster is easy. Shipping reliable software faster is the real challenge. A must-read for software engineers : engineering.atspotify.com/20…
4
27
298
31,221
True. Most people aren’t using today’s AI to its full potential.
Hi, I'm Felix. I'm an eng lead working on Claude. I love watching people take flight and do things they never thought possible. We often describe that as "being more ambitious" when using AI, which is tricky advice to follow. I wrote a tutorial: felixrieseberg.com/how-to-be…
6
4
1
158
77,410
Phawin retweeted
ชอบประโยคนี้มากเลย "Don’t let your kids best days financially be while they are living with you" ถ้าวันนี้ได้หมดทุกอย่างที่ต้องการแล้ว จะเหลืออะไรไว้ภูมิใจตัวเองในอนาคต youtu.be/H3CYQWfAMNo?t=3141&…
1
1
151
Apple says you need a Mac to build iPhone apps. Today I built one on Omarchy Linux, submitted it to the App Store, installed it on my iPhone over USB, and stopped it at a breakpoint in the debugger. No Mac anywhere. It's all open source: github.com/joshuaswarren/oma…
331
869
155
9,553
542,470
Phawin retweeted
GPT-6.1 Sol is our most demanded model pretty much ever both across both the API and subscriptions. Within ChatGPT & Codex, we were under heavy load, but have brough more capacity online and the speed should get much better in the coming hours, reaching almost twice the speed compared to what we served yesterday.
1,453
507
436
13,155
1,676,611
If you're learning system design, check out my fundamentals series: teapawt.net/system_monarch/status/…
1
1
12
70,923
Phawin retweeted
A pretty big change is that Pi now has MCP at the core. How is this even possible? What made us change our way? earendil.com/posts/you-said-…
78
135
68
1,871
342,317
Took the time and wrote down everything I have been learning about GPUs and CUDA. Consider checking it out!
19
173
12
1,440
287,961
ตอนจบใหม่อ่าน paper, ดู youtube คนอินเดียสอน, ไป join event เรียนรู้จากคนเก่งๆ, ฝากเจ้านายสั่งหนังสือจาก Amazon ใช้อะไรใหม่ๆ ที่ในไทยมีไม่กี่คนได้ใช้ จนปัจจุบันมันแพร่หลายไปแล้วหลายอัน ทุกวันนี้มี tools มากมาย แค่กระดิกตีนงานก็อาจจะเสร็จไปแล้ว 60-70% อะไรที่เคย learning curve แม่งมี lift ช่วยแทบหมด ถึงมันมีอะไรในรายละเอียดเยอะ แต่คนหัวไวๆ ก็ส่งงานไปได้แล้วพยายามเข้าใจมันไปด้วย ยังไงก็ไวกว่าคนรุ่นก่อนแน่ๆ เคยเจอ gen z เก่งๆ มาหลายคนส่วนตัวนี่ชอบมากๆ ทั้ง open, หัวไว​, ใช้ tools ใหม่ๆ เป็น ยังไงชีวิตก็ไปได้ไวกว่าคนอื่น คู่แข่งแทบไม่มี ถ้าจุดขายคนรุ่นใหม่คือ digital native การสร้าง folder ไม่เป็นนี่มันเอ๊ะไปจนถึงขั้น organize ชีวิตได้เลย จริงๆ เลิกพูดเรื่องคน gen นั้นนี้ อาจจะได้ มองทุกคนเป็นคนเหมือนกัน แล้วดูเอาว่าใครทำอะไรได้ ใครมีประสบการณ์เท่าไร ใครเรียนรู้ได้ เวลาเจอสถานการณ์ยากๆ แล้วแก้ปัญหาได้ แล้วคุณอยากจะทำงานกับใคร ที่ราคาเท่าไรพอ
Gen Y ก็หัดนึกถึงตอนทำงานวันแรกมั่งนะ มึงเป็นหมดทุกอย่างเลยหรอ ไม่เก่งโปรแกรมสำนักงานไม่ได้แปลว่าเขาจะทำอย่างอื่นไม่ได้นี่ มันเรียนรู้กันได้ เห็นคาดคั้นกับ Gen Z กันเก่ง อย่าโตไปเป็นอีแก่แบบที่ตัวเองเกลียดเลยค่ะ เด็กจะไม่เคารพเอานะคะ
370
504
28,259
Phawin retweeted
I understand the appeal in trying to find the first plausible fortress in our retreat from writing code, but if you think it's "architecture", I have bad news for you. The models are also very good at that.
421
277
135
6,442
617,050
I’m starting to not care that much about new model releases. I don’t really have an urge to go and try all of them out right away. Not sure if something changed from my side or if I’m already pretty happy with where ai coding was already.
29
3
3
77
5,989
the best way to learn inference is by implementing it yourself tensortonic.com
Wanted to do deep dive into inference engineering any good resource recommendations ?
10
156
1,552
89,583
new post: the senior engineer death spiral sunilpai.dev/posts/the-senio… a friend just started a big job and asked for some advice. so I braindumped a monologue about a super common failure mode I see with engineers and posted it here, hope it helps whoever it can.
278
638
275
7,274
1,854,164