LLMS

–

16 June 2026 5h24

Yeah, it really seems like the jailbreak was 'fix this code'.

→ View original post on X — @databricks

AI quality isn’t measured by token count, says Databricks scientist

By

@databricks

–

16 June 2026 4h28

"Just trying to use the most AI is like maximizing the number of lines of code you write. That's not a good measure of software quality, nor is the number of tokens." Databricks Chief AI Scientist @jefrankle kicked off tonight's DevConnect Meetup at #DataAISummit 2026 by

→ View original post on X — @theahmadosman

GLM is good but inconsistent and requires more steering than Kimi K2.7

By

@theahmadosman

–

16 June 2026 4h05

GLM is really good when it gets it right, but it is inconsistent out of the box and requires more steering in my testing than Kimi K2.7

→ View original post on X — @theahmadosman

Local LLMs Web Access with SearXNG, Firecrawl, Camofox

By

@theahmadosman

–

16 June 2026 3h21

PROP TIP Running LLMs locally? Give them web access My setup: – SearXNG: candidate source discovery – Firecrawl: known-URL scraping and crawling – Camofox: browser fallback when JS/interaction gets annoying Search → Extract → Interact Tell your favorite agent to set this

→ View original post on X — @testingcatalog

Codex supports Chrome DevTools protocol for inspecting and modifying websites

By

@testingcatalog

–

16 June 2026 2h53

OPENAI 🔥: Codex now supports Chrome DevTools Protocol for browser use. This is a huge superpower that will allow Codex to inspect and modify any website.

It is still a very early implementation, but I bet that in several years this will be a default browser capability. If… pic.twitter.com/mvLpRwnUXI
— 🚨 AI News | TestingCatalog (@testingcatalog) 16 juin 2026

OPENAI: Codex now supports the Chrome DevTools protocol for use in the browser. This is a considerable superpower that will allow Codex to inspect and modify any website. This is still a very early implementation, but

→ View original post on X — @localghost

Codex talks to Fable 5 via plugin and comparison with claude-channel-cli

By

@localghost

–

16 June 2026 1h51

Here's Codex talking to Fable 5 w/ my plugin.

Unlike calling the API, `claude-channel-cli` talks to the same full Claude Code harness as you. This means you can talk to either AI & they'll guide each other naturally with shared memories, decisions, and research. pic.twitter.com/GZAsdqnd5f
— Aaron Ng (@localghost) 15 juin 2026

Here is Codex talking to Fable 5 with my plugin. Unlike the API call, `claude-channel-cli` talks to the same full harness of Claude Code as you. This means you can talk to either AI and they will guide each other naturally with

Security bug discovery threatens model’s code writing capability

By

–

16 June 2026 0h34

We won't know until/unless we hear what the bug actually was If it really was "asking Fable to find security bugs in code found security bugs" then it can't be fixed without making the model useless for writing any code at all, which is one of the most important use-cases

AI finding security bugs threatens code writing use case

By

–

16 June 2026 0h34

We won't know until/unless we hear what the bug actually was If it really was "asking Fable to find security bugs in code found security bugs" then it can't be fixed without making the model useless for writing any code at all, which is one of the most important use-cases

Bug in finding security bugs threatens model’s code writing use-case

By

–

16 June 2026 0h34

We won't know until/unless we hear what the bug actually was If it really was "asking Fable to find security bugs in code found security bugs" then it can't be fixed without making the model useless for writing any code at all, which is one of the most important use-cases