Introducing AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents.
Long-horizon coding trajectories often accumulate failed attempts, stale hypotheses, and noisy tool outputs, making it harder for the agent to focus on what matters.
👉AutoCompact teaches coding agents to proactively call compact() when necessary, replacing noisy history with a clean working context for the next phase of the task.
(Glad to have contributed to this work with Xuan Zhang, @ltzheng01, Bo An, and @SimonXinDong)
Project page: https://t.co/c0ggSn8ePS
Most people quit because they forget that you have to be bad at something before you can be good at it. It's so obvious. You suck. Of course you're not going to win in 2 weeks. But if you can learn to enjoy extended periods of failure, you will make it very, very far in life.
🚨 BREAKING: OPENAI SAYS THEY’LL DO THE SAME THING THAT GOT ANTHROPIC BANNED
Sam Altman memo to OpenAI staff:
> “This is no longer just an issue between Anthropic and the Pentagon this is an issue for the whole industry and it is important to clarify our stance”
> “We have long believed that AI should not be used for mass surveillance or autonomous lethal weapons, and that humans should remain in the loop for high-stakes automated decisions. These are our main red lines.”
Altman on CNBC this morning:
>“I don’t personally think the Pentagon should be threatening DPA against these companies”
>“For all the differences I have with Anthropic, I mostly trust them as a company”
OpenAI is next…
we’ve entered the golden age of the idea guy
once resigned to “handling the business side”
the idea guy can now build anything
bound only by his creativity and clarity of thought