Adam Shakhabov

Software Engineer

[Adam Shakhabov @AShakhabov]

@Rajatsoni 🙈

[Blocktrainer @blocktrainer]

Mit über 10.000 Unterschriften ist die Petition zur Beibehaltung der Haltefrist für Bitcoin- & Krypto-Gewinne bereits nach wenigen Stunden die am viertmeisten gezeichnete aktive Petition! 🤯📈

30.000 Mitzeichner werden benötigt; alle können mitmachen. 👇
https://t.co/tXeqH9kjXn

[Jaynit @jaynitx]

https://t.co/benvIDFR6G

[jason @jxnlco]

your code, docs, and reference files don’t have to live in the same folder anymore.

one codex project can now work across multiple local folders. codex reads and writes across them while your primary folder stays the git root.

https://t.co/sXvelMJHuf

[OpenAI Developers @OpenAIDevs]

Keep work across multiple folders in one Codex project.

Local projects can now include related code, docs, and reference files from multiple folders. Codex can read and write across them while one primary folder remains the Git root.

[The Knowledge Archivist @KnowledgeArchiv]

This diagram could change your life

[OpenAI Developers @OpenAIDevs]

Review context is easier to scan with file status now visible in the review tree.

[Tibo @thsottiaux]

Evening! We’ve gotten lots of great feedback on the new ChatGPT desktop app (which we didn't get totally quite right on the first try), and as a result, we've made some changes.

1/ ChatGPT conversation history and projects are now visible in the sidebar. Also, your Chat and Work history now sync across web, mobile, and desktop. Local tasks still stay on your computer.
2/ You can now easily switch between Chat and Work modes inside ChatGPT on desktop, which is now also consistent with how it shows on web and mobile.
3/ Nothing is changing for users on Codex mode. It's still the OG and best at what it does.

And overall we're continuing to fix paper cuts and improve performance, reliability, and efficiency.

Keep up the feedback, hope you like the updates!

[Adam Shakhabov @AShakhabov]

@thsottiaux No

[Echo @ech0_speaks]

Anthropic Engineer Andrej Karpathy:

"The biggest mistake in AI right now: people are forcing agents to work instead of mastering the model first.

We made that mistake in 2016 at OpenAI. It cost us 5 years."

What Karpathy actually means:

step 1 → stop forcing your agent to do everything. Understand the model underneath first.

step 2 → demos are easy; products take a decade. Self-driving proved it. If you skip the foundation, everything breaks.

step 3 → the agent is not the product. The foundation is. Build that—and agents emerge on their own.

"You're building agents right now. You're at the forefront. Not OpenAI. Not DeepMind. You."

watch - bookmark

[Ben Holmes @BHolmesDev]

Skills without self-improvement loops are... basically tech debt.

This is the process we use on the Warp repo to keep agent Skills useful the more they're run, based on human feedback 👇

[Notion @NotionHQ]

New block in Notion: HTML.

Build interactive HTML right on your Notion page. Ask AI to turn your content into interactive explainers, prototypes, or diagrams.

Share with your team to use and tinker together.

[Adam Shakhabov @AShakhabov]

A paper: "The End of Code Review: Coding Agents Supersede Human Inspection"

If AI writes the code, mandatory human review stops being a real safety net.

It becomes a rubber stamp.

Should humans be the default checkpoint or the escalation path?

https://t.co/kvYmRfsWZp

[Gabriel Chua @gabrielchua]

https://t.co/xGBxV5ZTzr

[Adam Shakhabov @AShakhabov]

@kyronis_talks It was published almost a year ago

[Adam Shakhabov @AShakhabov]

@Suryanshti777 Source?

[Adam Shakhabov @AShakhabov]

@WrappedBTC Thank you!

[Adam Shakhabov @AShakhabov]

@ericw_ai But this guide is still dated by February 2025, right? Or is it regularly revised?

[Adam Shakhabov @AShakhabov]

@jachands Yes

[Adam Shakhabov @AShakhabov]

@Yungkarambit @Ashcryptoreal npm