{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Lenny’s AI Builders","title":"devs are paying double for the old GPT - i tested if they're right | LAB 0024","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/664cc18d\"></iframe>","width":"100%","height":180,"duration":847,"description":"devs are paying double for the old GPT on the API - GPT-5.6 Sol costs $4 in / $20 out per million tokens, GPT-6.1 Sol $2 / $10 - and swearing it's better than the new one. so i ran both on three of my real jobs (a broken test in Threadify, a video pipeline bug and my landing page copy), two runs each, with a blind judge from a different AI that only saw A and B.\n\nalso this week: GPT-6 Pro running agents in parallel, Claude writing 90% of Claude Code, X paying creators to post video, Claude Code answering sooner, and moving your AI memory into Grok Bot.\n\nthe practical: run your own model bake-off on your own work. give the prompt below to your agent. my recording cut out before i read it on camera, so here it is in full:\n\nI want to know which AI model is actually better for MY work - not on benchmarks. Run a blind bake-off.\n\nThe job: [paste one real task from your week - a bug, a failing test, a page of copy]\nModel A: gpt-5.6-sol    Model B: gpt-6.1-sol    (swap in any two models your CLI can run)\nPrices per million tokens (OpenAI pricing page, 17 Oct 2026): gpt-5.6-sol $4 in / $0.40 cached / $20 out; gpt-6.1-sol $2 in / $0.10 cached / $10 out.\n\n1. Make two clean copies of this project in a temp folder. Never touch my real folder.\n2. Run the job once in each copy with the same prompt and the same effort setting:\n   codex exec -m [model] -c model_reasoning_effort=medium --json \"[the job]\"\n   Time each run and save its token usage.\n3. Run my tests in both copies and note what passed.\n4. Hide the model names. Label the two results A and B in a random order. Ask a different AI to judge them\n   (for example: claude -p) - give it only the job, the two diffs and the test results, and ask for a 0-100 score\n   and one sentence why for each.\n5. Show me one table: tests passed, judge score, minutes, and cost at today's API prices. Then tell me which\n   model to use for this kind of job - and say plainly if it's too close to call.\nDrafts only: don't push, merge or publish...","thumbnail_url":"https://img.transistorcdn.com/P0B9fKUWl01KOkVXqQcDv5YBEKR1sflq-Hk71z-fa_U/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS84MzAx/ZGNmYzY1MmEwNjBk/NzUzN2NmODM3ZWUx/YzMzZi5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}