The model has two levels of reasoning, high and max, which push its reasoning and programming capabilities over a long horizon.
CODE
-
GLM-5.2: open weights MIT, 1M context, coding agents
By
–
Let's go, GLM-5.2 is released as an Open Weights model. tl;dr
– 1M context window
– Open weights under MIT license
– More powerful long-horizon coding agents
– Two reasoning modes: max and high
– Same API pricing as GLM-5.1 Zai says that GLM-5.2 has -
Mythos-class models: 4-8 months to harden IT systems
By
–
Assuming open models continue to lag about 8-12 months behind closed source (at least in coding), the countdown to hardening IT systems against Mythos-class models is now at 4-8 months Having publicly available and relatively safe defensive Mythos-class models today is important
-
Codex internal memory API endpoints for managing notes
By
–
not exposed to the end user (for good measure) but as an in-built tool that codex can call it can do the following: memories/list
memories/read
memories/search
memories/add_ad_hoc_note -
Run local models with agent harnesses like Codex or Claude Code
By
–
You can run local models at home and use any agent harness like Codex or Claude Code with them https://t.co/e5blwOYytx
— Ahmad (@TheAhmadOsman) 16 juin 2026You can run local models at home and use any agent harness like Codex or Claude Code with them
-
Use Codex to automate busy work and update memory
By
–
here are a few things that you should try to experience the future:
— Vaibhav (VB) Srivastav (@reach_vb) 16 juin 2026
– ask codex to use chrome and automate all your busy work like filling forms, capturing info
– ask it to update memory based on your recent sessions, PRs, artefacts on a project, watch it become better in… https://t.co/wxUxB1VlVRhere are a few things that you should try to experience the future: – ask codex to use chrome and automate all your busy work like filling forms, capturing info
– ask it to update memory based on your recent sessions, PRs, artefacts on a project, watch it become better in -
Origin: Cursor AI’s long awaited Git competitor announced
By
–
Cursor/Graphite’s @TomasReimers just announced Origin @cursor_ai
’s long awaited Git competitor, scalable for agent workloads, extensible with api and mcp, and built in merge conflicts and co failure agent resolution -
Increase in spending on coding agents and LLM gateway control
By
–
Like many organizations new to AI, our spending on coding agents has increased quite dramatically over the past few months. A key element of the LLM gateway we are developing (available in private preview right now) is the control of…
-
HarnessX self-compiles; Anthropic and Manus remove complexity iteratively
By
–
HarnessX: a harness that compiles itself. every harness improvement so far has come from a human editing code by hand. Anthropic strips planning steps out of Claude Code when a stronger model ships. Manus rebuilt its agent five times in six months, removing complexity each
-
Asking source of $13/day from Claude cost docs
By
–
Where did you get that $13/day number from? I found this page of the Claude docs but it's advising enterprise customers how much to budget when paying full API price for their team member https://
code.claude.com/docs/en/costs