black.terminal

Deep in vibe-coding mode. Developing AI coding infrastructure. Dev tools, scripts, apps. || Music & Sound design || Microsoldering & Repair

[marfin @marfinxx]

this is pure f*cking treasure

A Stanford AI research group found how to orchestrate Claude Opus 5.5 and GPT-6.1 Sol together, and it completely breaks the search scaffolding wall

most developers try to combine frontier models by chaining prompts in one context window or hardcoding rigid evolutionary loops. you burn tokens on context bloat and freeze models into fixed search rules that out-date themselves within 5 iterations

Stanford's architecture eliminates human-designed search scaffolding and splits the cognitive stack:

> search director: Claude Opus 5.5 plans the search, querying a persistent idea-graph where MAP-Elites and MCTS reduce to single Cypher queries
> candidate proposer: GPT-6.1 Sol explores high-entropy code variations inside isolated execution sandboxes
> zero context bleeding: sessions reset after each iteration to prevent prompt bloat while the graph stores lineage
> evaluator isolation: candidate code never touches the scoring process, stopping reward hacking and test leakage cold
> meta-agent distillation: an offline meta-pass extracts verified lessons and updates search guidance across branches

the benchmark metrics outclass standard discovery baselines:

> 3.2x lower model spend than fixed evolutionary frameworks
> 1st place rank across 7 competitive AtCoder heuristic contests against human competitors
> beats published SOTA on Anthropic kernel builder and 11 mathematical optimization tasks
> 0% reward hacks: candidate-controlled metric tampering eliminated

Opus directs the search graph. Sol explores the code

you stop writing rigid search harnesses. you let frontier models own the discovery loop

[Erick @ErickSky]

Hijo de su puta madre mira que está más arriba que el DeepSeek 4.1 flash y más barato.

Lo voy a probar y si es fiable como el DeepSeek, acabo de encontrar mi próximo main 🥰

[BridgeMind @bridgemindai]

I have never used Linux. Not once in my life.

Today that changes. I am trying Omarchy by DHH, a Linux distro built for AI agents and vibe coding.

Lifelong Mac user. This is a big deal for me.

Full review coming. If this is actually good for agentic workflows, it changes everything about how I build.

Does anyone have any tips?

[Anthropic @AnthropicAI]

The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees.

The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance.

Access to all other Claude models is not affected.

We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible.

Read our full statement: https://t.co/bwn0sximKZ

[black.terminal @Subkoks]

Statement on the U.S. government directive to suspend access to Fable 5 (@AnthropicAI) for all foreign nationals, both inside and outside the United States.
Yesterday, I migrated my entire coding setup from Opus 4.8 to Fable 5. Now I need a full rollback plan.

[black.terminal @Subkoks]

@OnlyTerp what? was claude code and now composer ass well with ultra code... whuaa. And when Codex?

[black.terminal @Subkoks]

Composer 2.5... Look at the - performance / cost

[Cursor @cursor_ai]

Introducing Composer 2.5, our most powerful model yet.

It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions.

For the next week, we’re doubling the included usage of the model.

[Cursor @cursor_ai]

Fast mode for Claude Opus 4.7 is now available in Cursor!

It's 2.5x the speed at 6x the cost. For most tasks, we recommend using the standard speed.

[black.terminal @Subkoks]

Amazon has committed $25 billion to Anthropic, pledging $100B+ in AWS spending over the next decade 💰
This launch is just the beginning of a much deeper AWS × Anthropic partnership. @claudeai @AnthropicAI @awscloud

[black.terminal @Subkoks]

@steipete : D

[Peter Steinberger @steipete]

RepoBar 0.5.0 is live

📋 GitHub refs from your clipboard
🔎 Issue, PR, and commit previews
🟢 Open/closed/merged at a glance
⚡ Fast lookups, cache-first

Tiny bar, much less mystery.
https://t.co/1tCKVNgTIQ

[black.terminal @Subkoks]

#coding @cursor_ai @claudeai @OpenAI @github stats.

[Peter Steinberger @steipete]

Released 🚦RepoBar 0.4.0.

This one makes the GitHub menu a lot smarter: persistent SQLite caching, fewer wasted API calls, visible rate limits, better Issues/PR loading, archive fallback support.

Tiny menubar app, increasingly useful daily tool. https://t.co/KYzCTtXF1O

[Shann³ @shannholmberg]

superpowers is still the simplest way to level up any project you're running in Claude

setup takes under 5 minutes. gets you to plan and map projects properly (code or non-code)

GPT image 2 generated a breakdown of the article below

save it and send it to your agent

[ClaudeDevs @ClaudeDevs]

New in Claude Code: /ultrareview (research preview) runs a fleet of bug-hunting agents in the cloud.

Findings land in the CLI or Desktop automatically. Run it before merging critical changes—auth, data migrations, etc.

Pro and Max users get 3 free reviews through 5/5.

[Cursor @cursor_ai]

We recently shipped quality-of-life improvements to the Cursor CLI to make working with agents in the terminal more delightful.

Use /debug to find root causes and fix tricky bugs that are hard to reproduce or understand.

[black.terminal @Subkoks]

Something #massive and good!!! VEGA - Off The Cuff Mix (May25") #SoundCloud
https://t.co/obmxaTehMw

[black.terminal @Subkoks]

First experience with Claude Dispatch feature on Desktop version and android claude app control my computer @claudeai

[black.terminal @Subkoks]

Claude biggest update : )) @claudeai