λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats) header
λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats) profile picture

Cats lover. Elm developers. Liverpool's fan.

Bangkok, Thailand
Joined January 2009
Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)Photo by λmp - เบาะรองนั่งของแมว 🔴 (@codewithcats)
λmp - เบาะรองนั่งของแมว 🔴 retweeted
I gave a talk recently about lessons learned running a Software Factory. Here are the best parts: 1. What is a software factory? => "A system of agents that build software, with humans occasionally in the loop. It's a higher layer of abstraction, where your engineering craft gets poured into agents instructions and infrastructure, as opposed to into software code." 2. They're made of: on-demand agents (the familiar), scheduled agents (underutilized by many), the correct instructions (skills, rules), and the correct environment (cloud, infra, connectors). 3. Good motivations to make a software factory: (1) you want to do less tedious work, less mindless nudging of agents, (2) you want to eliminate slop, (3) you want to increase trust in how your agents can build software. 4. Poor motivations: to automate everything as soon as possible, to just "vibe", to stop looking at code. 5. A software factory is simply programming, but now at a higher layer of abstraction. Instead of debugging stack traces, you'll be debugging (really!) agent runs, their reasoning, and tool calls. Instructions in natural language are code. Agent misbehavior is a bug, and your responsibility to fix. 6. If you think that is not programming, it's not the first time the industry has said so! When Assembly came out, John von Neumann disliked it, because machine code was the real deal. When PASCAL came out, it was not considered "real programming", FORTRAN was. And for many years, JavaScript was not considered a real programming language. 8. Invest in code reviews by *first* analyzing and introspecting what do *you* do when you're reviewing a PR, then teach agents to review like you do. Don't just send a dozen different LLMs to search for whatever. Make a list of the things you care about, then teach an agent to look for those during review. Make it systematic and invest in the reports it makes. 9. I've learned that I trust bot reviews now more than my own review, because they're *objective*, *systematic*, and *auditable*. Whereas my own human review is subjective, ad hoc and opaque (weeks from now, I won't know what my thought processes were when I approved some PR). 10. You should WRITE and READ English, not source code (except occasionally). Just like 4 years ago you AUTHORED JavaScript and REVIEWED JavaScript, without going down into the bytecode, you should remain in the same layer of abstraction. Authoring in a higher layer of abstraction but reviewing in a lower layer is bound to create a bottleneck in reviews, because the lower layers are inevitably more verbose. This means you should invest in a reporting process by which your agents abide when describing PRs. 11. A software factory makes it feasible to do things that were previously not, such as regularly deleting dead code, updating dependencies, eliminating patterns of tech debt. 12. Lesson: NARROW your agents with guardrails (rules, linting) and especially to FAIL CLOSED. Give instructions to your agents such that they should not be allowed to significantly deviate from the narrow direction you gave them. Agents should not try to hack around the constraints. You should give them a pristine and correct environment in which they operate. When they lack that environment, it's a bug and agents should fail, you should fix the environment. 13. Lesson: Premature automation is the root of all evil. Software factories give a lot of power, and you must put effort into pointing them in the right direction before you scale up automation. Focus on getting agents to behave correctly in a correct environment, with well constrained goals per agent, then scale it up little by little, monitor, and monitor. Excessive speed can make you crash into a million obstacles, sometimes with consequences.
39
21
4
195
16,873
λmp - เบาะรองนั่งของแมว 🔴 retweeted
We've given all Pro, Max, Ultra, and Team users one free full reset, across all models and limits. Use it anytime before December 10 at 2:00PM PT. We recently fixed a few small issues that used more limits than intended, and the Fable resets didn't do much for those of you who'd already hit your weekly limits for all models. While these issues didn't affect everyone, we want to make up for the trouble. You'll find it in Settings > Usage, or at clau.de/reset.
1,888
2,894
2,008
46,912
3,521,284
λmp - เบาะรองนั่งของแมว 🔴 retweeted
Applications are now open for the Anthropic Residency, a paid, fixed-term research program for academics, technical founders, and staff-level engineers who want to make AI safe and beneficial for everyone. No ML background is required. Apply by November 22: alignment.anthropic.com/2026…
1,232
3,214
936
40,532
14,959,109
ตอนหางานใหม่ทำไมยุ่งกว่าตอนมีงานทำล่ะเนี่ย 😂
32
Sadly, the company fired the cleaner and promoted the tornado. The cleaner is happy to be fired, though.
"Almost every software development organization has at least one developer who takes tactical programming to the extreme: a tactical tornado. The tactical tornado is a prolific programmer who pumps out code far faster than others but works in a totally tactical fashion. [...] In some organizations, management treats tactical tornadoes as heroes. "However, tactical tornadoes leave behind a wake of destruction. They are rarely considered heroes by the engineers who must work with their code in the future. Typically, other engineers must clean up the messes left behind by the tactical tornado, which makes it appear that those engineers (who are the real heroes) are making slower progress." @JohnOusterhout, A Philosophy Of Software Design, 2018 Sound familiar?
1
49
โทรศัพท์ดังไม่หยุดเลยเว้ย
29
λmp - เบาะรองนั่งของแมว 🔴 retweeted
Run an Elm program as a simple HTTP server! ✨ github.com/acadia-engineerin… ✨ Check out the full client/server/database example written in Elm/Acadia, and please share your results if you evolve it into something cool! Very curious to see what you can make!
9
41
5
260
13,564
The @DUPRpb service has been unusable for almost three days now. While I hope they can restore normal service soon, I find this situation unacceptable for something that has presented itself as a worldwide product.
399
λmp - เบาะรองนั่งของแมว 🔴 retweeted
How about we celebrate the great signings without disrespecting the PL champions?
Name a bigger upgrade in footballing history.
15,140
73,844
12,339
724,604
61,560,453
λmp - เบาะรองนั่งของแมว 🔴 retweeted
Last night at Anfield will stay with me forever - not because of one person's words, but because of how the entire football family stood together. To my @afcbournemouth teammates who supported me in that moment, to the @LiverpoolFC players and fans who showed their true character, to the @premierleague officials who handled it professionally - thank you. Football showed its best side when it mattered most. Scoring those two goals felt like speaking the only language that truly matters on the pitch. This is why I play - for moments like these, for my teammates, for everyone who believes in what this beautiful game can be. The overwhelming messages of support from across the football world remind me why I love this sport. We keep moving forward, together. 🙏🏾⚽ . . . . #FootballFamily #OnwardTogether #AFCB
4,109
15,944
915
142,450
4,510,704
λmp - เบาะรองนั่งของแมว 🔴 retweeted
Liverpool's 'summer of madness' is delighting its fans in equal proportion to upsetting rival supporters. Once the Ekitike deal is concluded, transfer fee outlay will hit £260m- with further expensive incomings expected. This thread explains how the club is financing it.
187
1,647
300
14,626
2,359,597
λmp - เบาะรองนั่งของแมว 🔴 retweeted
LIVERPOOL ARE THE 2024/25 PREMIER LEAGUE CHAMPIONS! 🏆
435
9,689
476
56,132
2,208,383
λmp - เบาะรองนั่งของแมว 🔴 retweeted
🏆 LIVERPOOL ARE CHAMPIONS! 🏆
1,855
28,054
2,607
127,894
7,774,843
λmp - เบาะรองนั่งของแมว 🔴 retweeted
ที่สุดของปี 2️⃣0️⃣2️⃣4️⃣
18
82
5,658
λmp - เบาะรองนั่งของแมว 🔴 retweeted
We are here for Ian Wright and Virgil van Dijk's friendship 😆 @IanWright0 🤝 @VirgilvDijk
92
533
42
9,250
728,565
λmp - เบาะรองนั่งของแมว 🔴 retweeted
🔴🛩️ Federico Chiesa: “I’m very happy, I can’t wait to become new Liverpool player. Me and my family, we’re so happy really”. “Let me say thanks to Juventus and the fans, they have been always special with me”. “Now it’s time for #LFC, I’m so happy. I can’t wait!”.
885
4,903
922
60,088
3,898,261
การเมืองไทยคลาสสิค ทะเลาะเรื่องเก้าอี้ ไม่มีประชาชนอยู่ในสมการ แต่คนก็ยังเลือกพวกนี้เข้ามาอีก
57
λmp - เบาะรองนั่งของแมว 🔴 retweeted
#พรรคประชาชน แสดงผล stretch goal แบบใหม่ คือเงินที่ได้ ทำให้พรรรครันอยู่ได้อีกกี่เดือน เล่นกับใจโหวตเตอร์สุด ๆ ถ้าแกไม่อยากอยากให้พรรครันเวย์หมด บริจาคสิ! แถมแจกแจงว่ารายจ่ายต่อเดือนพรรคใช้ทำอะไรบ้าง
37
1,656
32
1,496
140,284