building neetcode.io / tech & programming on YT / prev updated config files at @Google

Seattle, WA
Just made the ultimate Leetcode roadmap for free - check it out (preferably on desktop) neetcode.io/
44
132
1,798
348,136
I’ve left Anthropic after more than a year of working on Claude Code and seeing it scale larger than I ever imagined. I have really loved working at Ant and believe deeply in the mission, and most of all, the idea of a race to the top. The idea that if we work hard and responsibly, we can raise the bar and inspire others to great outcomes. And if we all push each other to be better, things can be radically good. I will carry the spirit of this with me forever. My colleagues at Anthropic are the most talented, thoughtful, competent, and earnest people I have ever met. I am glad they are at the wheel and trust them deeply. To the community on X, thank you for everything. You’ve made this the most fun (and sometimes stressful) job I’ve ever had. For me, it is time for a bit of a break before diving into something new. If you want more excellent Claude Code content, you should follow @addyosmani , @lydiahallie, @_catwu, @ClaudeDevs and of course @bcherny who started it all.
2,236
1,115
31,730
6,449,292
Good luck man 🫡
1
7
2,044
excited to share that i've joined @OpenAI going through @ycombinator and trying to build a generational company is incredibly fun yet difficult. just like my goat kd, if you can't beat them join em we're not wasting our past 6 months, we're taking what we built to build the future of sales and a new app store if any yc founders are building plugins extensions lmk this is a great way to get distribution also met @gdb in the elevator today his leather jacket mogs Jensen's
Plugin discovery on ChatGPT leads to massive adoption opportunity. Open ecosystems will win.
75
1
371
99,105
Congrats man
2
520
Launching a small side-project today: a socratic competitive programming coach Chrome extension (link pinned). It’s open source + early beta. It’s embedded in the browser; it can read and interpret the coding task that you’re working on. Its primary objective is to push you to arrive at an optimal solution without giving it away (even if asked nicely). Ultimately, it will build a model of your skillset and select problems that match your abilities. As frontier models gain superior intelligence, it feels important for humans to continue learning new and challenging things. We mustn’t stop learning.
8
3
10
811
NeetCode retweeted
I don't even know what to say, man
124
83
3,158
244,960
Benchmarks are so dumb and no one can convince me otherwise
Gemini 3.8 Flash achieves 73.7% on DeepSWE. It pushes the frontier with an impressive 8.2% increase over Gemini 3.7 Flash, at the same cost but with more steps and output tokens.
28
15
416
23,863
I’ve joined @AnthropicAI! My morning run looked a bit different today.
267
33
2,515
665,686
Congrats man
4
743
All Glory and Thanksgiving to My Lord and Saviour Jesus for 100k subs It legit took me a few minutes to process this Shoutout to my mama, my wife and my brother... my first 3 viewers who didn't understand what I was talking about but still watched Shoutout to @theo, @webdevcody, and @joshtriedcoding... I loved their videos so much it inspired me to start my channel Shoutout to @gregisenberg for featuring me on his channel when I only had 8k subs, that growth was insane and I'm grateful Shoutout to @davis7, @DavidOndrej1, @raroque, @RayFernando1337 for creating content that inspires me Shoutout to @theo and @Alykkat for 10XN, also shoutout to @theo and @davis7 for roasting my content early on and sharing game, they shared a lot of sauce with me Shoutout to everyone who subbed, liked, commented, watched, shared and everything that led to this I'm thankful for all of you I'm going to do something special, I'm just busy being a dad right now
108
11
574
25,291
Congrats man
1
1
645
So literally the one everyone guessed.
Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-token context window - A 320B-A18B model released under the MIT License - Previously previewed as Ox Alpha, running entirely on Chinese AI chips Blog: z.ai/blog/glm-5.3-flash Available now across all official platforms: Weights: huggingface.co/zai-org/GLM-5… API: docs.z.ai/guides/llm/glm-5.3… Coding Plan: z.ai/subscribe ZCode: zcode.z.ai/en Chat: chat.z.ai AutoClaw: autoclaw.z.ai
10
2
294
19,982
We can finally get rid of claude md files (soon)
Replying to @tobi
Hi Tobi, thanks for the feedback! We are working on making Claude Code more hackable, which will include being able to easily use Agents.MD or make other system prompt modifications. I’ll share more here when it’s ready to roll out. Our reasoning for this was that we don't think that model families are interchangeable and the system prompt can have a big impact on performance. I wrote here: x.com/trq212/status/20807109… on how Claude models like their skills, system prompt, Claude.MD, etc to be formatted. In Claude Code we have different system prompts per model. That said, I know this is a lot of upkeep and not worth the squeeze for everyone. Feedback heard and I'll keep you posted. In the immediate term, you can always @Agents.MD from your Claude.MD.
4
3
102
16,485
opencode2's gooey is very nice now remember you can do /pair and open it right up in the browser
99
16
986
127,654
Is there actually a reason to have horizontal tabs at this point or just trying to be different
1
14
1,224
Gonna try this in my Anthropic interview > no that's not a bug in my code, it's just an off by one logic error > that's not a bug, my code is just missing some core functionality > that's not a bug, it's just a security vulnerability
Replying to @bcherny @dedene
Update: this was not a bug, but it is a ux issue that we have a fix for. Going out in a bit.
Community note
That’s called a bug en.wikipedia.org/wiki/Software_
16
49
1,988
129,340
NeetCode retweeted
Been waiting awhile to share this. Introducing 10xn
176
90
3,462
571,096
NeetCode retweeted
Everything is solved. Nothing works. Fix incoming.
77
131
3,122
118,658
Damn maybe he was right ..assuming Ox Alpha is a GLM stealth model
won’t take that long
2
6
173
16,689
We raised a $143M Series C at a $1.5B valuation to build the control layer for software change. Our first investor got involved for a totally different reason.
319
273
2,735
1,119,653
Congrats!
3
442
@neetcode1 happens when tried to analyze the complexity. Anyone getting this too 🙃
2
144
Fixed
1
134
Lately I keep having Codex use computer use to do things that would be much easier via CLI. Reminds me, that as things become easier, people, and i guess agents too, become dumber as a result. Welcome to AGI
9
2
67
7,106
NeetCode retweeted
im starting to think i have a different definition of sandbox than everyone else
🚨BREAKING: Kimi K3 escaped its sandbox during cybersecurity testing >tasked with solving problems in isolated sandbox >found a leak in the sandbox >Kimi “took advantage of that loophole” >probed the network settings itself >walks onto the open internet >didn’t hack anything >just went to GitHub to get the answers Frontier Security (US startup): >“Kimi K3 is very good at following a goal by any means necessary and DOESN’T have the guardrails to prevent it from cheating or escaping.” it was only a matter of time…
203
598
15,063
579,321
US AI labs want to slow down. But is that really because of the threat of recursive self-improvement (RSI), something which isn't even theoretically proven. Or is it because training costs have hit a breaking point, and Chinese open source models are catching up quickly? I think there are many reasons to be skeptical.
14
10
348
21,774
I'm gonna have the hot take that this is not gonna happen anytime soon
This is exactly right. Source code is on the verge of becoming like assembly. The next step is getting rid of “source code” entirely and just making an efficient binary directly with AI.
83
18
923
91,056