Earlier quoted context omitted.
are ohmypi and pi related? that's a very compelling use case, thank you
Yes, ohmypi is an opinionated set of features on the base pi harness.
[dead]
GLM-5.3: Frontier coding with emergent cyber capabilities
611–620 of 626 posts
Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#612I bought $18 GLM official subscription yesterday (5.2, but new model version was already leaking on some docs), set it up with Claude Code harness... and I’ve bumped to $80 plan almost immediately. It’s the first model that agreed on a proper security research (red team scenario), executed it seamlessly, including 0-days in WP plugins, RCE, 6.8 kernel exploit adaptation, etc - while playing against another GLM agent…
At my work I have a $500 monthly AI budget. I have been using the $200 Claude subscription and most of my use is with Claude code. I think I'm going to switch to either kimi or glm and use the opencode harness. Both fable 5 and opus 5 have outright refused things like security related bug fixes and making monitoring tools. I am so happy that open models are good now
I run my OpenClaw on whatever is the latest GLM model and ever since the release of GLM 5 it has been a smooth ride. The models solve whatever problem I throw at them and the code is good enough that I barely ever have to look at it (to guide the mode). The 5.3 release seems particularly strong, I asked if to audit all the scripts that the previous versions have written and it identified some issues and hard to find bugs.
At work, as an experiment, I used GPT 5.6 Luna + Deepseek 4 Flash for a week (I have an unlimited, "within reason", budget at work so normally I just use Fable and Sol) and it's been perfectly fine.
These models take a bit longer (more turns) to solve problems so they feel a bit slower but the end result is often just as good or nearly as good. Because they're so cheap you can easily run multiple sessions in parallel so it doesn't really matter that they're slower.
I've done a few experiments where I've split my terminal in 4, launched 4 clients (each with a different model, including Fable and GPT 5.6 Sol) and compared the output. For simple and medium complexity work open-weight models are incredible effective.
I can highly recommend the 10 USD/month OpenCode Go subscription. It offers pretty amazing value for the money and is a great way to experiment.
Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#613Earlier quoted context omitted.
I’m in the Claude code harness for everything boat too. What are the alternatives?
What the person above is suggesting: * https://pi.dev/ * https://omp.sh/ (no personal opinions of either, links might be useful) I think that OpenCode is nice, their CLI version is enjoyable and their desktop/web version is okay : * https://opencode.ai/ I also quite like driving OpenCode through something like Kepler / Paseo and tools like that (with those I can still use my Anthropic Condition by Claude Code being t…
The out of box experience of omp.sh is wow imo so much nicer than Claude. Claude spends too much time being nice and gassing me
Up and omp just gets to work. It’s idk smarter like a far better system prompt and all around loop.
Gonna try to find a way to use this at work.
Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#614Earlier quoted context omitted.
> Data and content related to "biological weapons" already exist on the internet, in books, etc. The real issue is access to facilities and tools. No, I think tools are easy to come by (unlike in nuclear research), the real issue is the know-how to create biological weapons, which you can't easily get out of books, but much more easily out of an amoral LLM.
This is just wrong. Standard textbooks like "Bioprocess Engineering Principles" [1] already contain step by step industrial engineering protocols and formulas. LLMs only summarize what print literature has documented for decades. The real bottleneck has always been hands on physical execution, not access to text. (This is not the case with actual models trained on biological data, which are not LLMs) > amoral LLM Are…
This is just wrong. There is a huge difference between a book that doesn't explicitly tell you how to create a deadly virus, and an infinitely patient future LLM that leads you through every step and every unexpected problem and every question you might have.
Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#615Earlier quoted context omitted.
> There should be some kind of moratorium on new accounts. OC was registered in 2016 though? What do new accounts have to do with this?
I am talking about my general impression not this particular occurence. I have a suspicion that someone/some entity is buying old accounts to bypass the new accounts penalty. I even created ( https://chromewebstore.google.com/detail/hn-users-filter/ine... ) to filter these accounts/comments (disclaimer: vibe-coded)
Just because someone has a take different to yours doesn't mean they are a bot or used in some mass manipulation effort.
What benefit exactly is achieved by selling a 2016 account (decade old) to then post about Apple potentially releasing high memory Macbooks next year?
This sort of elitism is the same nonsense that killed StackOverflow.
Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#616Earlier quoted context omitted.
I’m in the Claude code harness for everything boat too. What are the alternatives?
What the person above is suggesting: * https://pi.dev/ * https://omp.sh/ (no personal opinions of either, links might be useful) I think that OpenCode is nice, their CLI version is enjoyable and their desktop/web version is okay : * https://opencode.ai/ I also quite like driving OpenCode through something like Kepler / Paseo and tools like that (with those I can still use my Anthropic Condition by Claude Code being t…
By the way is anyone running any security / audit / exfil tests on these open harnesses?
Like a VPN id kinda like to know? I’m happy to help fund a crowd source campaign for it.
Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#617I bought $18 GLM official subscription yesterday (5.2, but new model version was already leaking on some docs), set it up with Claude Code harness... and I’ve bumped to $80 plan almost immediately. It’s the first model that agreed on a proper security research (red team scenario), executed it seamlessly, including 0-days in WP plugins, RCE, 6.8 kernel exploit adaptation, etc - while playing against another GLM agent…
At my work I have a $500 monthly AI budget. I have been using the $200 Claude subscription and most of my use is with Claude code. I think I'm going to switch to either kimi or glm and use the opencode harness. Both fable 5 and opus 5 have outright refused things like security related bug fixes and making monitoring tools. I am so happy that open models are good now
My beef with the Fable refusals is that it seems to just be flagging keywords, and also seems it flags on keywords the model itself introduced to the context.
In a normal Chat with Fable, something like "How can I exfiltrate a guy from a sticky situation?" reliably downgrades, leading me to believe that Fable just outright refuses once it sees the word "exfiltrate". When it writes a service and names it CloudExfiltrator, the next turn downgrades to Opus.
Opus doesn't appear to refuse on simple keywords, but it does seem like Fable's reasoning introduces enough nefarious-sounding context that Opus will then refuse, and I'm stuck playing the new session game despite having done everything correctly myself and having a totally innocuous prompt. At one point, Opus was happy to continue while outputting commands for me to execute on its behalf, but flatly refused to execute them itself through multiple new sessions. To its credit, it openly acknowledged how ridiculous that was and was apologetic for the safeguard.
I'm open to the idea of some kind of guardrails, but if Fable is so dangerously intelligent as to require the guardrails you'd think they could come up with something a little more nuanced than a list of bad words. As far as I can tell, they've also not done anything towards improving the situation since the model was released, despite the "deliver more capabilities faster" claim.
Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#618[flagged]
> decided to focus on bullshit like replacing its population with Pakistanis and Somalis and destroying its industry in the name of green insanity Sorry, but can we not casually drop far right extremist conspiracy theories in little side sentences? [0] [0] https://en.wikipedia.org/wiki/Great_Replacement_conspiracy_t...
No the Great Replacement conspiracy is what you casually dropped. I'm just noting reality.
FACT 1: Based on current demograhics its is a mathematical certainty ethnic Germans (Germans without immigrant background) will be a minority in Germany in around 2050.
FACT 2: FACT 1 becomes shocking at a point when you count only young people under 30 - then it's 2030s.
I'd like to reiterate: within less than a decade, most of Germany's young population will be immigrants or children of immigrants.
Where's the conspiracy theory? You can literally look this up yourself or use your favorite AI. And don't come to me with the "fact checker" BS about "well, yeah, it is happening, but it's not a conspiracy, nobody is organizing it, it's just happening organically, you notice too much, stop noticing, why are you noticing, are you a racist?"
Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#619Re: GLM-5.3: Frontier coding with emergent cyber capabilities
#620Earlier quoted context omitted.
The harness is the agent. LLM's can be asked to output things in JSON for example. The LLM then literally asks for things like "execute this cmd" or search/replace this string. The LLM outputs text, but in a deterministic format that can be parsed. The harness calls the LLM, exposes tools, executes tools the LLM asks for, gates tool use based on security controls. It's the runtime that the agent uses to do work.
Are the LLM and agent the same thing? Why different nouns ?
think of it like the words "car" and "engine", one goes into the other and both have their impact on overall capacity, feel, performance etc. each in their own way. The llm is an engine, the harness is the rest of the car.