Testing AI Work Assistants on Trip Planning: ChatGPT and Claude Both Fumble Hotel Availability
giffmana · x · 2026-09-16
giffmana benchmarked AI work assistants on the canonical task "plan a trip from today's email" with all connectors enabled. ChatGPT Work browses well and finds trains/hotels, but fails to check room availability and prices, then gives up. Claude CoWork handles trains fine but also completely flukes hotel availability (no browser use). Gemini (still on Flash 3.6) is noisy and picks a suboptimal hotel initially, yet uniquely pulls real availability/prices via Google Travel — though it mid-conversation suggests Google flights to arbitrary destinations. Surprising how much OpenAI and Anthropic fumble this super canonical use case.
Related event: Hands-on test: AI travel agents stumble on hotel booking(3 posts)→
More from Models
- Google open-sources EmbeddingGemma 2: on-device multimodal search across photos, audio, docs — bigaiguy · 2026-11-02
- Anthropic's server-side rule reignites the case for owning open models over renting AI — alex_verem · 2026-11-02
- Epoch AI: open-weight GLM 5.3 exploited the patch gap to hack 6 Firefox releases at ~$1,000 each — rohanpaul_ai · 2026-11-02
- SemiAnalysis: safety classifiers sandbag scores of Opus 5.5 and GPT-6 Astra — morqon · 2026-11-02
- Liquid AI's 1.7B LFM3 becomes first local model to nail live fixtures lookup on a MacBook — NielsRogge · 2026-11-02
- Claude upgrade-page traffic rebounded to 17.6M in September, near May's 18.6M peak — firstadopter · 2026-11-02