event

GPT-6.1 Terra Release

21 items · started 2026-10-26 · closed 2026-11-14

  1. top is the best i got out of codex after days of going back and forth, on gpt 6.1 sol on extra high. every round it built another engine next to the old one (there are six sat in an archive folder now) and none of the fixes ever reached th…

  2. I find my agents have a lot of quit in them. They quit at the first obstacle and throw it back to me.

  3. anthropic dropped fable 5.2 yesterday, so I threw it against gpt-6.1 sol on the piston cup finale from Cars, rebuilt in 3D voxels. both got the exact same prompt and the same shots: mcqueen in the trailer, the race, the crash, the finish l…

  4. Particle-1 High and GPT-6.1 SOL each passed 28 of 30 Groovy trials; Particle Max passed 26. Compare coding, data science, provider costs, and evaluation limits.

  5. I was working on a deployment, using GPT 6.1 Sol, $100 subscription, and gave it all the requirements and preflight check instructions. It executed them, and after I gave the ok to merge the PRs and monitor the deployment, it tells me it w…

  6. Llamport: four OpenAI GPT models at 10% of the OpenAI price Llamport is a new upstream on AnyRouter. It serves four OpenAI GPT models at 10% of the OpenAI API list price, on the AnyRouter platform key or with your own Llamport key.

  7. Cost per successful task/PR is starting to become the default in how we measure coding agent impact, as cited by inference providers like Baseten as the "most important metric to track". On my repo, optimizing for this crowns GPT-6 Luna lo…

  8. I've configured Work to use GPT-6 Luna as its default model, and when I manually start a Work session, it correctly uses Luna. However, whenever ChatGPT automatically hands off a task to Work, it starts a new session using GPT-6.1 Sol High…

  9. Here's my list of agents that released something cool this month, Claude Code included. I dug through all the changelogs so you don't have to.

  10. could not extract summary

  11. Anthony Max@aanthonymaxI asked two models the same question: "Which is better, GPT 6.1 or Fable 5.1?" So, who’s right?5:17 PM · Nov 3, 2026·67Views15 Anthony Max@aanthonymaxI asked two models the same question: "Which is better, GPT 6.1 or…

  12. I've had the domain for a while as a someday-maybe and figured I had to jump onto the bandwagon! Partly as a challenge to stop navel gazing and ship something.

  13. Y Combinator's AI agent swarms in Minecraft and Mindustry, explained: what 50 agents and two rival teams show about running agents in groups Y Combinator and Olam Labs put 50 AI agents into one Minecraft world, then pitted GPT-6.1 Sol team…

  14. I didn’t want to copy and paste messages between coding-agent sessions or across vendors, so I built an MCP server that lets one model in one session talk to another model in a different session. They can even have a group chat.

  15. gpt_plays_games went live on Twitch. Catch up on their FINAL FANTASY VII VOD now.

  16. I recently migrated a production website from Vercel to my own VPS, using Coolify and Cloudflare. I had Codex (GPT-6.1 Terra High) handle pretty much the entire process.

  17. I recently tested the three Claude models (along with GPT-6.1 Sol and DeepSeek) on 50 tasks in Salesforce, grading each attempt on what actually changed. Wanted to share what I found.

  18. AI agents that read dense charts, navigate desktop apps, and process scanned documents are only as capable as the model behind them. OpenAI’s GPT-6.1 Terra,...

  19. 26th October 2026 - Link Blog GPT-6.1 Terra (via) It's always interesting to note which aspects of a new model are emphasized in the release announcement. In the case of GPT-6.1 Terra, OpenAI went with visual reasoning and computer use: We…

  20. GPT-6.1 Terra (Max) Intelligence, Performance & Price Analysis Model summary Speed GPT-6.1 Terra (Max) is amongst the leading models in intelligence and well priced when comparing to other models of similar price. The model supports text a…

  21. could not extract summary

← all threads