Skip to main content

Claude Code returns blank thinking blocks, but reasoning still costs you

Developers report model thinking blocks being returned empty or truncated

theregister.com ·22h ago

Claude Code returns blank thinking blocks, but reasoning still costs you

We haven't written up this one. The Register has the full story — the link below goes straight to it.

This story

This is one outlet's version. Read the fullest account.

75% of developers I surveyed prefer Claude Code - here's why they choose it over Codex zdnet.com
Claude Code can make videos: it records the app, narrates with ElevenLabs, and syncs audio to video automatically dev.to
Claude Code returns blank thinking blocks, but reasoning still costs you theregister.com

Read the original at theregister.com →

More in AI

RI, India to share AI, digital platforms for official statistics

RI, India to share AI, digital platforms for official statistics

Indonesia and India have agreed to exchange artificial intelligence applications and digital statistical platforms to expedite the modernization of their national data systems.

22h ago ·thejakartapost.com

I Asked Claude Code to Find Me a Trading Edge. It Killed Three Strategies First.

How I built a fully automated, rule-based Japanese stock research pipeline with Claude Code, J-Quants, and a macOS cron job — and why "the AI is not allowed to predict anything" turned out to be the…

22h ago ·dev.to

Bots Outnumber Humans As AI Takes Over Internet

Bots Outnumber Humans As AI Takes Over Internet

Bots have overtaken humans in web traffic, and non-human traffic could become 1,000 times larger than human traffic within five … Read More The post Bots Outnumber Humans As AI Takes Over Internet…

22h ago ·propakistani.pk

Correggere gli errori Lighthouse con un agente AI direttamente in Chrome DevTools

Dalla lista di audit falliti alle patch applicate: un flusso più rapido per sistemare problemi “di superficie” e prepararsi anche al web agentico.

AI agent integrated into Chrome DevTools for direct Lighthouse error correction.
Agent automatically runs Lighthouse checks and fixes identified issues.
Agent helps with surface-level errors like missing meta descriptions and color contrast.

22h ago ·dev.to

Peak XV Leads $45 Mn Bet On US-Based AI Code Testing Startup Blacksmith

Peak XV Leads $45 Mn Bet On US-Based AI Code Testing Startup Blacksmith

Peak XV Partners led a $45 Mn Series B funding round of San Francisco-based AI code testing startup Blacksmith at…

22h ago ·inc42.com

Chinese AI startup Zhipu releases GLM-5.3

Chinese AI startup Zhipu releases GLM-5.3

Zhipu said GLM-5.3 improved programming capabilities by 50% vs. GLM-5.2 in an internally built subjective evaluation.

21h ago ·techinasia.com

More from Friday 14 August →