Benchmarks and costs for o3 and o4-mini below. OpenAI said o3 hits SOTA performance across benchmarks for coding, real-world software tasks, and multimodality (MMMU). Some major efficiency leaps for both models compared to performance.
CODE
-
o3-mini Named World’s Top Competitive Coder by CFO
By
–
CFO Sarah Friar also recently said that o3-mini is already the No. 1 competitive coder in the world: pic.twitter.com/wsHPQqKI5I
— Rowan Cheung (@rowancheung) 16 avril 2025CFO Sarah Friar also recently said that o3-mini is already the No. 1 competitive coder in the world:
-
OpenAI releases o3, o4-mini reasoning models and Codex CLI
By
–
BREAKING: OpenAI just released o3 and o4-mini, the company's two newest reasoning models. o3 is OpenAI's 'most advanced' reasoner yet, while o4-mini brings strong results at lower costs. Also launching is Codex CLI, a new open-source coding agent. More info in thread below:
-
OpenAI o3 and o4-mini Models Available via Chat Completions API
By
–
Both OpenAI o3 and o4-mini are also available to developers today via the Chat Completions API and Responses API. The Responses API supports reasoning summaries, the ability to preserve reasoning tokens around function calls for better performance, and will soon support built-in
-
Codex CLI: Lightweight Coding Agent for Command Line
By
–
Codex CLI is a lightweight coding agent that runs directly from your command line. It’s been such a joy partnering with @fouadmatin on this. We can’t wait to see what you’ll build with Codex!
-
OpenAI Launches Codex CLI with Auto Mode
By
–
BREAKING 🚨: OpenAI introduces Codex CLI – a command line coding agent. Codex also supports "auto" mode, where the agent is given full rights to operate on its own.
— 🚨 AI News | TestingCatalog (@testingcatalog) 16 avril 2025
Codex is open-source? 🔥 pic.twitter.com/TcQDG42CdxBREAKING : OpenAI introduces Codex CLI – a command line coding agent. Codex also supports "auto" mode, where the agent is given full rights to operate on its own. Codex is open-source?
-
LangGraph Agent LLManager Open Source Release Announced
By
–
We're excited to open source LLManager, a LangGraph agent which automates approval tasks through human-in-the-loop powered memory! Alongside the open source repo, we also released a YouTube video taking a deep dive into its architecture, and use cases (link in reply)
-
Matrix Transpose Simplification: From Complex to Elegant Solution
By
–
TFW you flip so many matrices that you wind up with:
C = (A.t @ B.t).t
And realize you can just do:
C = B @ A -
Firecrawl LinkedIn scraping works only when logged in
By
–
ok weird because firecrawl playground definitely looks like it can grab the data from linkedin BUT its because its my fucking own profile and im logged in i guess. i use socialdata and proxycurl for APIs – they dont have MCPs yet and i dont fancy making them…
-
Firecrawl MCP Integration with Claude Desktop for Social Media Scraping
By
–
who's got @firecrawl MCP working with claude desktop to scrape linkedin and X?