Theo (@theo) shared a photo on X of a four-node Mac Mini cluster named ProMini, Mini10g, DeskMini, and ClawMini, networked over 10GbE with roughly 96GB of aggregate unified memory across four 24GB nod…
Anthropic rolled out Projects within Claude Code, letting a single conversation spawn parallel cloud sessions that pass context between each other and keep running after the session closes, with Anthr…
A viral short video titled 'AI Limit Exploit: How Theo's Token Trick Went Viral #shorts' has surfaced on YouTube, showcasing a method to bypass AI token limits, though the video's content is not detai…
Theo launched AgentCloud, an MCP-first iOS simulator cloud that gives MCP-compatible cloud agents like Cursor Cloud a true iOS simulator to install apps, tap around, and test features end to end. The …
A survey of coding agent reliability and two conference talks argue that the bottleneck in AI systems is no longer the model but the surrounding infrastructure, with over 30% of code changes now mergi…
A developer argues that memorizing common coding interview patterns is not cheating but a realistic job skill, citing data suggesting 80% of interview problems stem from five core patterns. The post c…
Anthropic's Claude Opus 5, released as its latest flagship model, posts benchmark scores on par with GPT-5.6 but has drawn widespread user complaints of verbosity, overreach, and worse coding judgment…
A developer discovered that OpenAI's Codex model manifest for GPT-5.5 contained a large frontend guidance block with specific UI rules, suggesting that GPT's perceived poor UI taste may stem from hidd…
A developer created claudex, a tool that allows users to run OpenAI's GPT/Codex models through Claude Code's interface and terminal UX. It uses a local CLIProxyAPI server to translate and route reques…
A user known as Theo spent over $200,000 in tokens using OpenAI's GPT-5.6-sol model, praising its quality but noting that the $200 Codex Pro subscription limits are too easily reached, though OpenAI h…
Developer Theo reports that GPT-5.6 Ultra performs better in Anthropic's Claude Code than in OpenAI's Codex, expressing frustration over the discrepancy.…
Theo and Ben spent $224,700 in tokens on early access to OpenAI's GPT-5.6 Sol model, concluding that reverting to GPT-5.5 was so unpleasant they stopped coding for the day. The model is a strong codin…
Claude Sonnet 5 is reportedly dead in the water, according to a screenshot of total-run costs shared by Theo, suggesting the model's performance or viability is failing.…