AI圈报
教程 / 实战普通

An 8B Agent That Thinks Without Writing Tokens Beats GPT-5.6 Luna on GAIA. Not on HLE

信息来源：DEV Community·
GPT

内容摘要

HybridAgent reasons partly in hidden states, then acts in text. Open weights, MIT. The wins are real, so are losses, and your traces can't read its thoughts.
内容分类AI 教程与实战
内容层级普通情报
发布时间（北京时间）
本站收录时间（北京时间）
信息来源DEV Community
站内情报编号intel-1479bf866fdd61d2a6c09b0a
阅读原始信息 ↗更多教程 / 实战

相关推荐

综合分类、实体标签与信息来源匹配

教程 / 实战普通
Codex Swapped Its Default Model and Retired GPT-5.5 in 15 Days. Did Your Evals Notice?
Codex made GPT-6.1 Sol its default on Sep 29 and dropped GPT-5.5 for ChatGPT sign-ins on Oct 14. Pin your agent's model and log it with every result.
信息来源：DEV Community · ChatGPT / GPT
教程 / 实战普通
ChatGPT UTM Bug Sent Referral Traffic to Direct During the GPT-6 Rollout
A temporary change in how ChatGPT handled outbound links distorted a key marketing metric during the...
信息来源：DEV Community · ChatGPT / GPT
教程 / 实战普通
Gemini Gems become skills in November and custom GPTs retire on December 11. What to copy out first.
If you built a Gem in Gemini or a custom GPT in ChatGPT, it is about to be converted into something...
信息来源：DEV Community · ChatGPT / GPT / Gemini
教程 / 实战普通
Why did my Claude Haiku calls start 400ing? Three AI API changes that break code quietly
Three AI API changes from the last two weeks that quietly break shipped code: Claude Haiku 5.5 migration 400s, Managed Agents web_fetch gating, and the GPT-6 plan split.
信息来源：DEV Community · GPT / Claude
教程 / 实战普通
My benchmark scored GPT-5.4 mini 1.00 by silently skipping the 3 questions it failed
This is a submission for the Kaggle Benchmarking Challenge GPT-5.4 mini got a perfect 1.00 on my...
信息来源：DEV Community · GPT
教程 / 实战普通
GPT-2 is the transformer plus five decisions, and inference is a different program
Originally published at cchinchilla.dev. Part 6 of From code to weights, a 12-part series on ML...
信息来源：DEV Community · GPT
教程 / 实战普通
Spellcheck can't fix "chai GPT": building an LLM caption checker on $5 a month
Here's a line from YouTube's auto-captions on a lecture about attention in neural...
信息来源：DEV Community · GPT
教程 / 实战普通
Same prompt, four models: what Opus, Sonnet, Astra and Sol each got wrong
I ran one prompt through four models last week. Opus 5.5 and Sonnet 5.5 in Claude Code, GPT-6 Astra...
信息来源：DEV Community · GPT / Claude
教程 / 实战普通
Opus 5.5 pricing vs GPT-6 Sol: which is cheaper per task?
Opus 5.5 pricing: $4/$20 per million tokens, 60% off cache reads. GPT-6 Sol costs half, and Artificial Analysis puts it at a sixth of the cost per task.
信息来源：DEV Community · GPT
教程 / 实战普通
OpenAI DevDay 2026: every announcement, with prices and availability
OpenAI DevDay 2026 recap: dots, GPT-6.1 Sol at $2/$10, Ultrafast, Pro 500, Decisions API, Codex cloud, Agents API and Sign in with ChatGPT.
信息来源：DEV Community · OpenAI / ChatGPT / GPT