I can't shake of the feeling that Googles Deep Think Models are not really different models but just the old ones being run with higher number of parallel subagents, something you can do by yourself with their base model and opencode.
No it's not because cost is much lower. They do some kind of speculative decoding in monte-carlo way If I had to guess as humans do it this way is my hunch. What I mean it's kinda the way you describe but much more efficient.
The idea is that each subagent is focused on a specific part of the problem and can use its entire context window for a more focused subtask than the overall one. So ideally the results arent conflicting, they are complimentary. And you just have a system that merges them.. likely another agent.
They could do it this way: generate 10 reasoning traces and then every N tokens they prune the 9 that have the lowest likelihood, and continue from the highest likelihood trace.
This is a form of task-agnostic test time search that is more general than multi agent parallel prompt harnesses.
10 traces makes sense because ChatGPT 5.2 Pro is 10x more expensive per token.
That's something you can't replicate without access to the network output pre token sampling.
"It was in the reign of George III that the aforesaid personages lived and quarrelled; good or bad, handsome or ugly, rich or poor, they are all equal now."
Besides that blog post obviously being written by AI, can someone here confirm how credible the hype about openclaw is? I'm already very proficient at using Claude Code anywhere, so what would i gain really with openclaw?
I played with it extensively for three days. I think there are a few things it does that people are finding interesting:
1. It has a lot of files that it loads into it's context for each conversation, and it consistently updates them. Plus it stores and can reference each conversation. So there's a sense of continuity over time.
2. It connects to messaging services and other accounts of yours, so again it feels continuous. You can use it on your desktop and then pick up your phone and send it an iMessage.
3. It hooks into a lot of things, so it feels like it has more agency. You could send it a voice message over discord and say "hey remember that conversation about birds? Send an email to Steve and ask him what he thinks about it"
It feels more like a smart assistant that's always around than an app you open to ask questions to.
However, it's worth stressing how terrible the software actually is. Not a single thing I attempted to do worked correctly, important issues (like the discord integration having huge message delays and sometimes dropping messages) get closed because "sorry we have too many issues", and I really got the impression that the whole thing is just a vibe coded pile of garbage. And I don't like to be that critical about an open source project like this, but I think considering the level of hype and the dramatic claims that humans shouldn't be writing code anymore, I think it's worth being clear about.
Ended up deleting it and setting up something much simpler. I installed a little discord relay called kimaki, and that lets me interact with instances of opencode over discord when I want to. I also spent some time setting up persistent files and made sure the llm can update them, although only when I ask it to in this case. That's covered enough of what I liked from OpenClaw to satisfy me.
> You could send it a voice message over discord and say "hey remember that conversation about birds? Send an email to Steve and ask him what he thinks about it"
if one of my friends sent me an obviously AI-written email, I think that I would cease to be friends with them...
> You could send it a voice message over discord and say "hey remember that conversation about birds? Send an email to Steve and ask him what he thinks about it"
Ah, so it's a device for irritating Steve, got it.
> “hey remember that conversation about birds? Send an email to Steve and ask him what he thinks about it”
Isn’t the “what he thinks about it” part the hardest? Like, that’s what I want to phrase myself - the part of the conversation I’d like to get their opinion on and what exactly my actual request is. Or are people really doing the meme of sending AI text back and forth to each other with none the wiser?
I think in the context of business communication; yeah a lot of people are doing that. Which, to be honest, I don't think it the worst thing ever. Most corporate communication is some basic information padded out with feigned personal interest and rehearsed politeness, so it's hardly a huge loss.
For personal communication between friends it would be horrible. Authenticity has to be one of the things I value most about the people I know. Didn't mean to imply from that example that I did or would communicate that way.
The value of openclaw as I understand it is separate context management per venue (per dm, per channel, per platform, etc) and clever tricks around managing shared memories and state.
Well, that and skills to download more skills. It’s a lot faster and easier to extend OC than CC via prompts. It also has cron and other take-initiative features.
I had it hack up a poller for new Gitea notifications (for @ mentions and the like) that wakes up the main bot when something happens, so I have it interacting with a self hosted Gitea. There wasn’t even a Gitea skill for it, it just constructs API requests “manually” each time it needs to do something on it. I guess it knows the Gitea API already. It knew how to make a launchd plist and keep the poller running, without me asking it to do that. It’s a little more oriented toward getting things going and running than CC, which mostly just wants to make commits.
Somehow i want to ask what's the actual job of those former software engineers. Agents everywhere, on your local machine, in the pipeline, on the servers, and they are doing everything. Yes, the specs also.
Someone still has orchestrate the shit show. Like a captain at the helm in the middle of a storm.
Or you can be full accelerationist and give an agent the role of standing up all the agents. But then you need someone with the job of being angry when they get a $7000 cloud bill.
That's not what i am seeing being played out at a big corp. In reality everyone gets thrown under the bus, no matter if c-level or pleb if they don't appear to know how to drive the ai metrics up. Just being a PM won't save your job any more than that of the dev who doesn't know how to acquire and use new skills. On the contrary, jobs of the more competent devs are safer than those of some managers here who don't know the tech.
It's insane that they concluded the builtin introspection skill for claude documentation should do a web search instead of simply packing the correct documentation in local files. I had the same experience like you, wasting tokens and my time because their architecture decision doesn't work in practice.
I have to google the correct Anthropic documentation and pass that link to claude code because claude isn't able to do the same reliably in order to know how to use its own features.
reply