NeetCode

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

[NeetCode @neetcode1]

Just made the ultimate Leetcode roadmap for free - check it out (preferably on desktop) https://t.co/nkWe0WcfKn

[NeetCode @neetcode1]

@RuhanPonnada @OpenAI @ycombinator Congrats man

[NeetCode @neetcode1]

@essamsleiman @boriskurikhin here

[Valentin Ignatev @valigo]

I don't even know what to say, man

[NeetCode @neetcode1]

Benchmarks are so dumb and no one can convince me otherwise

[Datacurve @datacurve]

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.

[NeetCode @neetcode1]

@edwinarbus @AnthropicAI Congrats man

[NeetCode @neetcode1]

@Rasmic @theo Congrats man

[NeetCode @neetcode1]

So literally the one everyone guessed.

[Z.ai @Zai_org]

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: https://t.co/tzOmB7gdZP

Available now across all official platforms:

Weights: https://t.co/9LRMahY9Wa
API: https://t.co/VcaQnzYmS9
Coding Plan: https://t.co/Nk8Y98HNhU
ZCode: https://t.co/Peepqv4XSx
Chat: https://t.co/WCqWT0qCQb
AutoClaw: https://t.co/aGEG5HqTTb

[NeetCode @neetcode1]

We can finally get rid of claude md files (soon)

[Thariq @trq212]

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: https://t.co/WCXcDYJlwq 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.

[NeetCode @neetcode1]

@thdxr Is there actually a reason to have horizontal tabs at this point or just trying to be different

[NeetCode @neetcode1]

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

[Boris Cherny @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.

[Theo - t3.gg @theo]

Been waiting awhile to share this.

Introducing 10xn

[Andrew Ambrosino @ajambrosino]

Everything is solved. Nothing works. Fix incoming.

[NeetCode @neetcode1]

Damn maybe he was right

..assuming Ox Alpha is a GLM stealth model

[jietang @jietang]

@elonmusk @teortaxesTex won’t take that long

[NeetCode @neetcode1]

@coderabbitai Congrats!

[NeetCode @neetcode1]

@Harriso42593357 Fixed

[NeetCode @neetcode1]

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

[Rhys @RhysSullivan]

im starting to think i have a different definition of sandbox than everyone else

[NeetCode @neetcode1]

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.

[NeetCode @neetcode1]

I'm gonna have the hot take that this is not gonna happen anytime soon

[Elon Musk @elonmusk]

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.

[NeetCode @neetcode1]

Just had Fable (on high in cursor) tell me it can't verify something locally, because some of my md files are stored in my prod db.

But they're not, they're stored in a public github repo.

People that aren't actually reading or understanding what the agent tells you, don't catch these things, so they think there's no reason to read anything anymore.