SOFTWARE

–

13 November 2025 10h10

Baidu released ERNIE 5.0 Preview omnimodal foundational model. It is now available for testing on Ernie Chat.

→ View original post on X — @bcherny

Claude Code WebFetch Tool Adds Markdown Accept Header

By

@bcherny

–

13 November 2025 7h43

In the next version of Claude Code, Claude’s WebFetch tool automatically adds Accept: “text/markdown, *” to requests which helps docs sites provide token-efficient docs

→ View original post on X — @skathirmani

Tiger Analytics Hiring ETL Testing SQL Python Professionals

By

@skathirmani

–

13 November 2025 5h29

Job alert. Tiger Analytics is looking for ETL testing, SQL and Python professionals https://
linkedin.com/posts/harish%7
E64651993_tigeranalytics-walkindrive-hiring-activity-7394362644138323968-8Wx2?utm_source=share&utm_medium=member_android&rcm=ACoAAANCzNYBKgyKbDw069-q7BKGJ0qzZoL-8Xw
…

GPT-5.1 Drops Em Dashes on Command

By

–

13 November 2025 1h31

GPT-5.1 does NOT use em dashes anymore—in case it is specified in custom instructions! Instruction following is also getting much better in comparison to GPT-5.

GPT-5.1 ‘Thinking’ and ‘Instant’ versions launching

By

–

12 November 2025 20h12

BREAKING : OpenAI is rolling out GPT-5.1 to ChatGPT users as per multiple reports. GPT-5.1 comes with "Instant" and "Thinking" versions. "GPT‑5.1 Thinking varies its thinking time more dynamically than GPT‑5 Thinking."

Tavus Preview: 5 AI Agents for Work

By

–

12 November 2025 17h32

BREAKING 🚨: Early preview of Tavus 👀

There, you will be able to work with 5 human-like agents via text, voice and video chats. Work apps can be connected as well, so AI agents can execute tasks autonomously.

The AI office 🤖 https://t.co/lKLTsl8pdE pic.twitter.com/sb4LgWxuxY
— 🚨 AI News | TestingCatalog (@testingcatalog) 12 novembre 2025

BREAKING : Early preview of Tavus There, you will be able to work with 5 human-like agents via text, voice and video chats. Work apps can be connected as well, so AI agents can execute tasks autonomously. The AI office

→ View original post on X — @godofprompt

A working Obsidian clone built in one prompt, zero errors

By

@godofprompt

–

12 November 2025 14h18

Here are some demos.

Built a working Obsidian clone in one prompt.
2,000 lines of code.
Zero errors.

Even entry-level engineers can’t do that. pic.twitter.com/1hiw6dD06H
— God of Prompt (@godofprompt) 12 novembre 2025

Here are some demos. Built a working Obsidian clone in one prompt.
2,000 lines of code.
Zero errors. Even entry-level engineers can’t do that.

→ View original post on X — @godofprompt

xAI drops Grok-4-Fast: 2M-token reasoning model, faster, cheaper

By

@godofprompt

–

12 November 2025 11h30

xAI just dropped a monster: Grok-4-Fast Its a 2M-token reasoning model that’s faster than anything in its class and cheaper than lunch. $0.20 in / $0.50 out per million tokens. That’s 6× cheaper than Grok-4-0709 with the same brain. The wild part? It’s not just speed. It’s