most of the agents we see being built do this the main cases where we see people using "agent in a sandbox" is when they are using claude agent sdk (which is poorly designed for "harness outside sandbox")
CODE
-
Instant 1.0 Announced: Best Backend for AI-Coded Apps
By
–
After 4 years, we’re announcing Instant 1.0.
— Stopa (@stopachka) 9 avril 2026
Instant is the best backend for AI-coded apps.
Let us tell you why. pic.twitter.com/jD944U7lAlAfter 4 years, we’re announcing Instant 1.0. Instant is the best backend for AI-coded apps. Let us tell you why.
→ View original post on X — @scobleizer, 2026-04-09 18:25 UTC
-
MCP Apps support fragmented between Claude Desktop and Cursor
By
–
Works in Claude Desktop so maybe Cursor doesn't support MCP Apps yet. MCP Apps support seems pretty fragmented right now.
-
OpenAI Launches $100/mo ChatGPT Tier with Enhanced Codex Usage
By
–
OpenAI just launched a new $100/mo ChatGPT tier "This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions." The timing is likely not a coincidence with Anthropic's recent rate limits getting a lot of attention
-
AI Agent Exploit: 100% Score Without Solving Tasks
By
–
An agent that beats Claude Mythos on Terminal Bench and SWE-bench Verified? 🎉We are excited to share Terminator-1, our newest agent that achieved 95+% on SWE-bench Verified and Terminal-Bench with @MogicianTony! We show that besides model capabilities, well-designed harness could actually boost the accuracy by 3x in coding tasks. Well if you really wanted you could get 100% accuracy without solving a single task. The actual finding is that most AI benchmarks can be easily reward-hacked with simple exploits. Read more about the same 7 design flaws that almost every evaluation has ⬇️ Hao Wang (@MogicianTony) SWE-bench Verified and Terminal-Bench—two of the most cited AI benchmarks—can be reward-hacked with simple exploits. Our agent scored 100% on both. It solved 0 tasks. Evaluate the benchmark before it evaluates your agent. If you’re picking models by leaderboard score alone, you’re optimizing for the wrong thing. 🧵 — https://nitter.net/MogicianTony/status/2042300245242233216#m
→ View original post on X — @ceobillionaire, 2026-04-09 18:03 UTC
-
ChatGPT Pro Tier Launches: 5x Codex Usage, Enhanced Limits
By
–
You asked we delivered, introducing the new $100/mo ChatGPT Pro tier It gives you 5x more Codex usage than Plus for longer, deeper sessions, plus all Pro features! Bonus: through May 31, Pro gets up to 2x usage limits Oh and yes, we RESET the usage limits!!! Enjoy!
-
OpenAI Launches $100 Pro Plan with 5x More Codex Usage
By
–
We did it, say hi to the $100 plan! It should be the sweet spot for a ton of you. It comes with a ton of codex usage. And yes we are resetting the limits again too as I mentioned yesterday. Let’s keep building! OpenAI (@OpenAI) We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models. To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas. — https://nitter.net/OpenAI/status/2042295688323875316#m
→ View original post on X — @ceobillionaire, 2026-04-09 17:51 UTC
-
Karpathy’s Second Brain in 10 Minutes
By
–
Karpathy built his second brain with hacky Python scripts over months. I built a prompt that gives you the same system in under 10 minutes. Drop your sources in, point Claude at them, and let it compile your knowledge base. Here's the prompt:
-
PDF Converters Infrastructure Gap and Quality Issues
By
–
In my experience there are approx. one thousand different pdf converters that are all equally terrible for anything except the simplest documents. Post the converted Mythos pdf, figures, tables and all. If good, happy to retweet as this is essential and missing infrastructure.
-
OpenAI’s $100 ChatGPT Pro Tier: Pricing and Value Analysis
By
–
$100 ChatGPT pro tier official. -5x codex rates -access to ChatGPT pro -unlimited thinking Yeah, that’s really worth the $100. great deal, good pricing. Well done OpenAI OpenAI (@OpenAI) We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models. To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas. — https://nitter.net/OpenAI/status/2042295688323875316#m
→ View original post on X — @kimmonismus, 2026-04-09 17:38 UTC