The Anthropic model degradation lately is no joke. Opus 4.6 just tried to use Perl for something!
LLMS
-
MiniMax and Ollama fixes released in latest update
By
–
We added some fixes for the new MiniMax and Ollama in this release as well – just hearing far fewer complains there so didn’t mention these. Check the changelog if you’re curious – we wanna be a great harness for *any* model!
-
Codex Harness and Verifiable Stop Conditions for Model Control
By
–
At least if you use codex harness that should not be needed much anymore. If you provide a verify-able stop condition the model is quite relentless
-
xAI Unveils Voice API for Developers
By
–
One of the xAI API's most underrated features is our Voice API (which includes text-to-speech and voice agents). We're giving all developers access to literally the same tech that powers experiences like Grok in Tesla. docs.x.ai/developers/model-capabilities/audio/text-to-speech [Translated from EN to English]
→ View original post on X — @scobleizer, 2026-04-12 01:45 UTC
-
Making GPT More Agentic: Configuration Options
By
–
Try one of the options in my tweetstorm if you feel GPT is not agentic enough in the default settings.
-
Native Codex as OpenClaw Harness Configuration and Thread Management
By
–
2) Native Codex as the OpenClaw harness: plugins.entries.codex.enabled = true
agents.defaults.model = "codex/gpt-5.4"
agents.defaults.embeddedHarness = { runtime: "codex", fallback: "none" } Codex owns threads, resume, compaction, app-server execution. https://
docs.openclaw.ai/plugins/codex-
harness
… -
GPT-5 Strict Mode: Addressing Lazy Agent Execution Issues
By
–
Two experiments in the next @openclaw to address some "GPT is lazy" issues: 1) Strict mode: agents.defaults.embeddedPi.executionContract = "strict-agentic" This tells GPT-5.x to keep working: read more code, call tools, make changes, or return a real blocker instead of
-
Running parallel agents interactively and deterministically with git worktrees
By
–
In the Space today I broke down how I run parallel agents both interactively & deterministically > Ask the main agent to spin up workers (ex: Kimi Cli) > Go fully deterministic with Python/Bash loops w/ separate git worktrees as backups Turning this into a Skill for u guys rn
-
MiniMax M2.7 Open Source with State-of-the-Art Performance
By
–
We're delighted to announce that MiniMax M2.7 is now officially open source. With SOTA performance in SWE-Pro (56.22%) and Terminal Bench 2 (57.0%). You can find it on Hugging Face now. Enjoy!🤗 huggingface：huggingface.co/MiniMaxAI/Min… Blog: minimax.io/news/minimax-m27-… MiniMax API: platform.minimax.io/
→ View original post on X — @scobleizer, 2026-04-12 01:00 UTC
-
Why Anthropic Refused Release Most Powerful AI Model
By
–
Why Anthropic Refused to Release Its Most Powerful AI Yet? https://
youtu.be/86jjRbZQNQ4?si
=6MmWtXwJX2nj4QU0
… via @YouTube #mythos #anthropic #GenerativeAI #AI #artificialintelligence #GenAI #LLMs @PawlowskiMario @chidambara09 @Ym78200 @CurieuxExplorer @efipm @bigfundu @sayedflah @Ronald_vanLoon