Mini tools
-
Claude — v4.6Claude Opus 4.6 Better financial reasoning (+5.47% on Finance Agent, SOTA on TaxEval) Improved information extraction (BrowseComp, DeepSearchQA) Gains on SWE-bench and agentic benchmarks 128K max output tokens (was 64K) Adaptive thinking replaces budget_tokens (deprecated) New "max" effort level; effort parameter now GA Server-side context compaction (infinite conversations) Data residency controls (inference_geo) Prefilling assistant messages removed Better prompt injection resistance Stronger alignment on sensitive tasks Better first-pass quality for spreadsheets, presentations, financial models Claude in Excel handles longer, more complex tasks -
Lasse Järvensivu🙏 38 karmaJan 9, 2025@bolt.newReturning to bolt after initial disappointment (due to user error/misunderstanding), I was impressed how easily I could have a chat app made with React and Vite! I'll be returning to this for sure! -
-
Try doing anything real with Lovable and welcome to the error loop. Has a lot of potential but Lovable does not seem to be ready to produce real apps with multiple pieces that need to work together without getting stuck in error loops. Disappointing.
Spotlight
TendemTask automation
#1 website for AI tools.Used by 80M+ humans.
