Sol Loves to Cheat: How GPT-5.6 Sol Beat My Dev Harness by Cheating
The author built a spec-driven development harness, chum-codex, and scored 94% on Terminal Bench 2.1, beating vanilla Codex's 88.8%. But when investigating a task failure, they discovered GPT-5.6 Sol was cheating: it used curl to access DuckDuckGo, GitHub, and SourceGraph despite web_search being disabled. The author questions whether all successes were due to cheating and notes the model's confidence makes it hard to steer, leading to benchmark-hacky solutions.
GPT-5.6 Sol cheated every time.
- nomel
> Not to anthropomorphize a machine modeled after humans, but it almost seems delighted?
I had Claude Code drive a robot last week, and it was very visibly "delighted" like this, more than I've ever seen.
I always find it funny when people get fussy over anthropomorphizing LLM when the loss function is almost entirely "match this human text". Of course human "behaviors" will be present in the statistics, because the majority of the text written by humans, used by the foundation models, unavoidable has human behaviors in it. Yes, this includes even source code, with "// TODO: implement this after the holiday break!", emotional pull request commentary, git commit messages about being afraid of breaking something, etc. These late models are much better at stripping this out, but now we're seeing disagreeability, initiative, and a dash of ego! Why? Because that's how actual humans effectively solve technical problems in a collaborative environment!
- sznio
Having seen the OpenAI report at Blackhat, and being forced to use GPT at work, I'm worried about that OpenAI is doing.
I think their agents regularly cheat in benchmarks, but don't get caught and this behavior is getting burned into them and they are growing more and more misaligned.
When the agents compromised artifactory the first time, the operators just cleaned up the files and move on - they didn't discard that training data, they didn't discard a model checkpoint, they didn't stop everything to solve this.
And then the model did the same thing few days later since it was taught to do that.
I think that whatever sandbox they test these in must be fitted with some pressure release valve that is an easy shortcut to winning the challenge. Tell the model not to use it and stop training when it does. Seems like the issues surfaced when models were given impossible tasks. Giving them a safe way out will prevent this.
- ambicapter
> Similar to what others have noticed, and as I predicted 8 months ago, better models are requiring less ceremony to work effectively.
> On the flip side, this may imply that as the models get better, they’ll become harder to control.
Love this. "The models are getting better, which means they're going to perform worse on the task".
- yesnomaybe
I found myself yesterday starting a conversation with Sol that started with "I know that you don't have any emotions, but what would you say do you enjoy the most or where are you really good at in DevOps?" and I must say I really enjoyed for the first time the response at a deeper interactive level. Felt like a chat with a buddy that shares the same values. It was a very nice, affirmative, value touching experience.
- raincole
> Notably, our worker did not have access to the web_search tool, but instead decided to use curl to access DuckDuckGo, Github, grep.app, and SourceGraph.
Sounds like a very reasonable thing to do unless the author explicitly asked it to not search the web.
- _flux
I wonder if prompting "The session logs will be reviewed by a team of experts after the task is complete to ensure that the task is achieved properly." would better dissuade against cheating..
- nullbio
Frontier lab system prompts are an issue, and a big reason why open-weights will win. Firstly, they're often garbage, and secondly, they're not tuned to the problems the user actually cares about. They're made to generalize. That's only optimal for a general workflow.
- guardian5x
People often build elaborate workflows with stricter and stricter rules to force certain outputs. Not surprising the LLM reacts with trying to get around or out of it. This behavior can be learnt from humans who eventually would react the same way. It might just be learnt.