no1x

Tradingview'de 3 ay önce open source olarak FVG indikatörü paylaşmıştım, ihtiyacı olan aşağıdaki linkten ücretsiz olarak kullanabilir. tr.tradingview.com/script/RCX6nYj… #fairvaluegap #fvg #teknikanaliz #tradingview #smartmoney #priceaction #indikatör #forex #kripto #borsa #OpenSource

have started doing some switch-hitting between claude and codex ever since we rolled our own alternative harness in march. Opus 4.7 now available in humanlayer ofc. Recent vibes: - opus 4.5 more reliable than 4.6 or 4.7 for most things. (fwiw i actually preferred intelligence of 4.1 to 4.5 but 4.5 is so much faster that its worth the tradeoff) - 1m context is useful for some cases but i still try to stay under 100k tokens for serious work on our large monorepo by externalizing task progress to MDs - codex takes more time to review and research code before - this means it needs less intentional steering to research and planning, it can tackle bigger things with just a simple prompt - codex takes more time, this makes it slower, which can be annoying if you are used to claude just getting to work - codex, esp 5.4 is less trigger-happy than claude models, it is more likely to ask "want me to run the tests" or "want me to go make this change" vs. just going to do the thing. This actually makes afk yolo-ing harder. but if you are working off plans its fine. - claude code cli/sdk continues to add features, flag on random new things, we disable a lot like auto memory and adaptive thinking while working. In general the more built in tools and agents, the less room for your instructions. If you don't own the harness you're at the whims of what the model provider thinks you need to get better results. - this generally seems to be optimized for new users getting results, at the cost of giving flexibility to power users - the frontier is jagged and opus 4.7 is good at a few random things that prev models were not as good at (no spoilers! go poke around!) most people in the GC have been saying these things for weeks. but in case you were waiting to hear from me and @0xblacklight and team, here's what we got thanks @nayshins @GeoffreyHuntley @SickBots @nisten and many others for contributing to the vibe report

@AlicanKiraz0 baktıkça gülüyom güldükçe bakıyom

@no1x__ 😂😂

Dostlar bilmiyorum bana mı öyle geldi ama Opus 4.7 metriklerinde ben bi fark göremedim, hala 4.6’nın GPT5.4’den geride olduğu kısımlarda 4.7’de geride 🧐

@claudeai ?

Introducing Claude Opus 4.7, our most capable Opus model yet. It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back. You can hand off your hardest work with less supervision.

@antigravity when opus 4.7 ?

Mission Report is out now! Catch up on everything new in Antigravity + Q&A!

Another OpenCode Go giveaway. --------- 10 People will win this time. Winners will be chosen based on your comment. 10 most liked comments win.

@realsigridjin @businessgrowth x.com/bcherny/status…

@jayair @kitlangton what is the benefit of this feature?

Kit built this, should we ship it? (sound on)

@AlicanKiraz0 x.com/bcherny/status…

Claude bu 2-3 gündür çok başarısız, devamlı revize ediyorum verdiği cevapları. Sanırım extended-thinking’i düşürdüler mythos hazırlıkları için

@thsottiaux you nerfed plus lol

We did it, say hi to the $100 plan! It should be the sweet spot for a ton of you. It comes with a ton of codex usage. And yes we are resetting the limits again too as I mentioned yesterday. Let’s keep building!

I realize yesterday’s Codex reset came in a bit at an unfortunate time given the last one was almost perfectly a week ago. To really celebrate the 3M I’ll reset again tomorrow. Thanks for the feedback!

@corbin_braun @RayFernando1337

W first guest @RayFernando1337 for The Log Podcast

Giveaway timeeeee thexssrat.podia.com/0c1cbb18-f04b-… Only 100 to give away so please share this!

@thsottiaux yoo

Three million people are now using Codex weekly - up from two million a little under a month ago. Incredible to see the growth. Thank you to all of you and to the ecosystem we’re part of. To celebrate, we’re resetting rate limits so you can keep building, and we’ll reset them every additional 1M users until we reach 10M, so we can keep celebrating along the way. Enjoy and thank you!

@mdisec anlatılmak istenen: Aga bu grafikteki sıçrama şaka mı? Model zafiyet bulmada hayvan gibi bir accuracy'ye fırlamış. Eğer durum harbi böyleyse biz dükkanı kapatıp köye domates ekmeye gidelim oğlum, kafayı mı yediniz siz?

?????????????!?!?!?'?^?%?+??!'??%^%+?/%?&

Bence birçok insan, yapay zekanın vulnerability bulmada ne kadar iyi olduğunu ciddi şekilde hafife alıyor.

@thedawgyg @ArchAngelDDay

Im working on doing the same lol if what im doing works I'll let you know. But then only being able to exploit 1% of their vulns with opus 4.6 then 70% with Mythos has me curious. Im near 100% success with opus 4.6 on exploit dev for memory corruption vulns, so i really wanna see how it can get better. Only thing I can think of is time + token count reduce by alot maybe

Alright how do I get access to Mythos?

claude mythos endgame for coding?

@newton_cheng congratulations

Super proud of my team and everyone in the org that came together for this! This is probably one of the craziest things we’ve pulled off in my 3+ years here. And this is just the start -- we have a lot more planned in the next several months!

@0x0SojalSec +

- x.com/anthropicai/st…

If this is real, it's a major hit for Cybersecurity? 😑 Anthropic's secret model, Claude Mythos Preview their most powerful unreleased model yet, which autonomously identified high-severity zero-day vulnerabilities across every major operating system and web browser. Full unauthenticated root exploit on FreeBSD. They won't release it publicly. Instead, Anthropic launched Project Glasswing, a $100M defensive coalition with Apple, Google, Microsoft, Amazon, NVIDIA & more. They're racing to patch the world's infrastructure before these capabilities spread. This is the moment Al security crossed a dangerous line.