←
Basix121,549 posts
Basix avatar

Basix

@Basix1120

Software Engineer | 고용주의 의견과 무관합니다 | spin-spin.com/Basix1120 | 🇰🇷🇬🇧

◷ Joined August 2019▧ 3,073 Photos and videos
Basix avatar
Basix@Basix1120·13m

한국에서 유튜브 프리미엄으로 번들링 맞았다고 AI Pro에 유튜브 프리미엄 안 끼워주는거 ㅈㄴ째째한것같음

𝒽𝓂 avatar
⟳ Basix retweeted
𝒽𝓂@hmartapp·37m

오르카 깃허브 레포가 갑자기 펑되는 전대미문의 상황 속 오르카? 내리카? 라는 글을 보고 터진 나에게 반성하며.....

Post attachment

Orca's GitHub organization has been flagged and is currently hidden from public view. We haven’t received a clear reason for the restriction and believe this may be a mistake. Orca is an open-source project with 129k+ GitHub stars, and our development and community activities remain active as usual. @github, could you please help review our organization and restore public access? github.com/stablyai/orca We’ll keep everyone updated here.

Theo - t3.gg avatar
⟳ Basix retweeted
Theo - t3.gg@theo·3h

They should have just named this Gemini 5 and nobody would have blinked

Why the fuck is nobody talking about Neon? This model is so good wtf

Hoshino Lina / 星乃リナ 🩵 3D Yuri Wedding prep!!! avatar
⟳ Basix retweeted
Hoshino Lina / 星乃リナ 🩵 3D Yuri Wedding prep!!!@Lina_Hoshino·13h

Oh no. Not another one. 😭 *Hurriedly disables http2 everywhere*

Pre-auth RCE in nginx is the bug every hacker dreams of finding. It almost never happens. Today we’re disclosing nginx2root: five nginx vulnerabilities, and an exploit that takes an unauthenticated attacker all the way to root. One of themhits the default config. If you run nginx, patch now. Then read: nginx2root.com CVE-2026-123007, CVE-2026-123634, CVE-2026-123633, CVE-2026-121810, CVE-2026-113425

Wes Bos avatar
⟳ Basix retweeted
Wes Bos@wesbos·12h

No one wants to use your agent We want to use your thing with our agent

We messed up. We built an AI PM, but nobody wants another agent. They want to use their own. So we rebuilt the platform. Introducing Modem 2.0: finds problems buried in customer channels, tracks them, and follows up when fixes ship. Works with the agents you use every day.

1:08
Gwen (Chen) Shapira avatar
⟳ Basix retweeted
Gwen (Chen) Shapira@gwenshap·Nov 17

From @almoggavra at @QConSF : Using S3 as your storage layer gives you a “pick 2 of 3 tradeoff” between: - latency - durability - cost Because the way to reduce cost is to buffer writes into larger batches. Larger batches are cheaper. If you ack writes when they reach S3, they have higher latency. If you don’t, you have lower durability (you can lose writes when the buffer is lost). Great concept to have when reasoning about systems!

Nathan Flurry 🔩 avatar
⟳ Basix retweeted
Nathan Flurry 🔩@NathanFlurry·11h

quick tip we learned the hard way @ rivet: jev does not reason ...which is by design ...and we should have rtfm first ~ we started by prompt-engineer to ask something like: ``` 𝚜𝚎𝚟𝚎𝚛𝚒𝚝𝚢 = 𝚊𝚜𝚔( "𝚐𝚒𝚟𝚎 𝚖𝚎 𝚝𝚑𝚎 𝚜𝚎𝚟𝚎𝚛𝚒𝚝𝚢 𝚘𝚏 𝚝𝚑𝚒𝚜 𝚒𝚜𝚜𝚞𝚎. 𝚏𝚘𝚛 𝚎𝚡𝚊𝚖𝚙𝚕𝚎, 𝚜𝚎𝚟-𝟷 𝚒𝚜 𝚇, 𝚜𝚎𝚟-𝟸 𝚒𝚜 𝚈, 𝚜𝚎𝚟-𝟹 𝚒𝚜 𝚉, 𝚎𝚝𝚌", 𝚘𝚞𝚝𝚙𝚞𝚝𝚜=[𝚂𝙴𝚅𝟷, 𝚂𝙴𝚅𝟸, 𝚂𝙴𝚅𝟹, 𝚂𝙴𝚅𝟺] ) 𝚛𝚎𝚝𝚞𝚛𝚗 𝚜𝚎𝚟𝚎𝚛𝚒𝚝𝚢 ``` normally, an llm would spend reasoning tokens to come to a descent conclusion but doing this with jev gives meh results, and defeats what makes jev awesome ~ after rtfm, we split it up in to tiny prompts like this: ``` 𝚒𝚜_𝚍𝚘𝚠𝚗 = 𝚊𝚜𝚔("𝙳𝚒𝚍 𝚝𝚑𝚎𝚒𝚛 𝚙𝚛𝚘𝚍𝚞𝚌𝚝𝚒𝚘𝚗 𝚜𝚎𝚛𝚟𝚒𝚌𝚎 𝚐𝚘 𝚍𝚘𝚠𝚗 𝚘𝚛 𝚋𝚎𝚌𝚘𝚖𝚎 𝚞𝚗𝚞𝚜𝚊𝚋𝚕𝚎?") 𝚒𝚜_𝚋𝚕𝚘𝚌𝚔𝚎𝚍 = 𝚊𝚜𝚔("𝙰𝚛𝚎 𝚝𝚑𝚎𝚢 𝚋𝚕𝚘𝚌𝚔𝚎𝚍 𝚠𝚒𝚝𝚑 𝚗𝚘 𝚠𝚘𝚛𝚔𝚊𝚛𝚘𝚞𝚗𝚍?") 𝚒𝚜_𝚋𝚛𝚘𝚔𝚎𝚗 = 𝚊𝚜𝚔("𝙸𝚜 𝚜𝚘𝚖𝚎𝚝𝚑𝚒𝚗𝚐 𝚒𝚗 𝚁𝚒𝚟𝚎𝚝 𝚋𝚛𝚘𝚔𝚎𝚗 𝚘𝚛 𝚏𝚊𝚒𝚕𝚒𝚗𝚐?") 𝚒𝚏 (𝚒𝚜_𝚋𝚕𝚘𝚌𝚔𝚎𝚍) 𝚛𝚎𝚝𝚞𝚛𝚗 𝚂𝙴𝚅𝟷 𝚒𝚏 (𝚒𝚜_𝚍𝚘𝚠𝚗) 𝚛𝚎𝚝𝚞𝚛𝚗 𝚂𝙴𝚅𝟸 𝚒𝚏 (𝚒𝚜_𝚋𝚛𝚘𝚔𝚎𝚗) 𝚛𝚎𝚝𝚞𝚛𝚗 𝚂𝙴𝚅𝟹 𝚛𝚎𝚝𝚞𝚛𝚗 𝚂𝙴𝚅𝟺 ``` which works like a charm (example screenshot of real-world classifier below) ~ any time we find a ticket that isn't weighted well: - we give the ticket to an llm with what we expected - llm adds it to a test suite - llm adjusts decision logic - backtests new decision logic on old issues within a few tickets the classifier logic was really solid ~ this is a feature of jev, not a limitation in practice, it gives more control over how each decision is weighed than a generic llm which makes it easier to reason about, monitor, and back test how agents will behave ~ for reference, this is how many jev questions we ask for a few of our classifiers in our internal support tool: support classification and customer status: 13 severity: 6 team replies and problem identification: 6 follow-up timing: 6 linked dependencies and later conversations: 4 addressed teammate: 2 conversation grouping: 2 ~ all that to say, jev is awesome

Post attachment
Lolifox avatar
⟳ Basix retweeted
Lolifox@lolifoxapp·19h

Update your uBlock Origin (UBO) immediately, be sure you have at least version 1.76.0 or above A simple browser restart should be enough

Theo - t3.gg avatar
⟳ Basix retweeted
Theo - t3.gg@theo·3h

Gemini 4 Neon might actually be a good model. Fuck.

I...don't hate this model. Yet at least. Gonna keep pushing. 👀👀

Ovais Tariq avatar
⟳ Basix retweeted
Ovais Tariq@ovaistariq·11h

"S3-compatible" should be measurable. So we wrote an open-source test suite and ran it against Tigris, R2 and GCS. Out of 94 tests, Tigris passed 83, R2 53 and GCS 48.

예차니즘✨ avatar
⟳ Basix retweeted
예차니즘✨@yechanism_·11h

GPT 모델...얘네는 그냥 '근본'이 다름. 얘네들은 사용자의 "의도"에 관심이 없음. 그냥 프롬프트로 들어온 최신 사용자 메시지에 과도하게 좁은 시야로 작업함. - 나: "이러한 버그가 있어. 고쳐" - GPT: "고쳤습니다" - 나: "근데 이러면 안되지 않아?" - GPT: "맞습니다 제가 간과했습니다"

I took this to heart and spent the last few hours doing another deep dive on GPT-6.2 Astra tl;dr - things are better than when I tested, but IMO still "directionally, very bad" I'm going to keep using the same example I've hyperfixated on since the start: "why is creating a worktree so slow?" I had a long thread trying to diagnose perf issues while using t3 code on a particular VPS. 2 of the 3 were fast, 1 was really slow. I asked astra outright "why is this so slow?", and it said a bunch of gibberish. I followed up with "I feel like I'm going insane, can you just tell me the cause of the slowness?" I'll give you the answer upfront: this VPS uses a virtual disk that is slow as shit, my other VPSs have physical NVME drives that are faster. Image 1 is from before the fixes Tibo mentioned. It shows an unnecessary graph, focuses too much on pnpm and file systems, bolds irrelevant text, and brings up ram just as much as it (subtly) mentions drive speed. Image 2 is of Opus asked same thing. It opened with the important part in bold: "Slow disk, made worse by VDO". Ideal! Image 3 is 6.2 Astra post-fixes Tibo mentioned. Better? Absolutely. Much more concise. Sadly, it still focuses way too much on second-order problems that are a small % of the cause. "XFS over a compression and deduplication layer on a virtual disk." - so close, but still a miss. I think this perfectly encapsulates the problem I have with 6.2 Astra. It doesn't miss anything. It's SO thorough. But in it's thoroughness, I find it misses the most important thing: the actual point. It wants to know everything, and then it wants to share everything. It doesn't understand what is and isn't important. Did it say anything wrong in my screenshots? Not really. But IMO, it still entirely failed to miss the point of my question, and gave an answer that was too focused on accuracy and not enough on clarity. In the wise words of Michael Seibel: "Most aim for 100% accuracy, and they end up with 50% clarity. Aim for 100% clarity, 80% accuracy". Silly way of putting it, but I genuinely wish OpenAI models would lie to me a LITTLE more so I could better understand the vibe, instead of having my time wasted by all these useless details.

Post attachmentPost attachmentPost attachment
赤スラ avatar
⟳ Basix retweeted
赤スラ@red_slime_cyz·18h

これは本当にあり得るパターンです。氏名ではなくコードで引くのが普通ですが、複数現場で目撃済です。 サンプル: if(kaiin_code == 1111111) { // 山田太郎専用処理(20171121 お客様要望) … } 影響力が大きい顧客への対応でありがちです。無茶な要望をシステム側で吸収する体制です。

本番データじゃないとテスト出来ないって、 if(name == "山田太郎"){   //山田太郎専用処理 } if(name == "田中二郎"){   //田中二郎専用処理 } こんなのがあるの??