AI Models thread

[mid_gen]

*Another suggestion for an AI subforum while I'm here. You can't search 'AI' because it's too short. So many discussions scattered across different subforums.....

Specific thread for the latest AI model releases.

Today Mistral Large 4 has been released. It's nice to have a European option, and open-weights too. Will be giving it a whirl later today.

My daily drivers at the moment are Claude Opus 5.5 and Fable 5.1 depending on the work. I'm also using Deepseek v4.1 Flash as a summariser for some automations.

I ensure my pipelines are all compatible with Claude Code and Opencode so I've always got a route to switch models and toolchains. I may configure a mistral agent that I can call from Claude Code to adversarial review things.

 

[Dr Jack]

I feel like I should try out some other models and settings, but I just use Opus 5.5 on medium for everything. It seems to just work for the things I want it for without chewing through my subscription usage.

 

[mid_gen]

I feel like I should try out some other models and settings, but I just use Opus 5.5 on medium for everything. It seems to just work for the things I want it for without chewing through my subscription usage.

Just bear in mind Claude Max won't be subsidised the way it is now forever.

I rolled my own activity/issue tracking system on Monday, with CC and Opencode plugins, so it tracks all token usage across all providers.

I'm burning about $40-50 a day on Opus at API rates.

This is why I continually evaluate various other models and providers and make sure I can switch as and when I need to. Deepseek V4 flash was the first one that I really felt was capable and affordable enough to use as a daily driver coding agent at API rates. v4.1 and GLM 5.3 flash have pushed the boundaries even further....and the distils will keep getting better.

For now though Opus 5.5 and Claude Max are a luxury I will make the most of. Although I do keep meaning to try Codex again...I do have to focus my time and effort on my business, not evaluating LLMs....and Opus 5.5/Fable just gets **** done really fast and is very affordable still.

 

[Dr Jack]

Just bear in mind Claude Max won't be subsidised the way it is now forever.

Yeah, absolutely, and I'm curious to know how the whole AI thing looks after that happens. With the rate that open models and distils are improving, I think there's a good chance that by the time it does happen there will decent alternatives available. I don't see anything about Claude that particularly locks me in. So long as there's a tool a bit like Claude Code it can slot right in and do the same job.

That said, I don't get even get through a Pro subscription at the moment. I haven't got into it as much as you, but even when I've used it to vibe whole tools (a tracking system last weekend, and a bit of software to help make art for my game yesterday) for me it hasn't hit the limits.

 

[sHo0sH]

I've been hitting limits on a 5x max plan each week for the last few weeks.

All based off 1 Claude Opus 5.5 ultracode review to improve how my game can become beautiful (Gettin Opus 5.5 to carry out the work on Medium). It's scheduled about 150 hours of agentic workload which I'm chipping away at and am very interested to see what it can output. As a non-coder it blows my mind.

Got it doing its own dev blog here: https://pixelpunk-journal.pages.dev/

 

[mid_gen]

I've been hitting limits on a 5x max plan each week for the last few weeks.

All based off 1 Claude Opus 5.5 ultracode review to improve how my game can become beautiful (Gettin Opus 5.5 to carry out the work on Medium). It's scheduled about 150 hours of agentic workload which I'm chipping away at and am very interested to see what it can output. As a non-coder it blows my mind.

Got it doing its own dev blog here: https://pixelpunk-journal.pages.dev/

Ultracode is way overkill for a task like that, you're just demolishing your usage limits for little tangible benefit. Ask Fable to do a review (not ultracode) for a plan, implement with Opus 5.5.

 

[Jim99]

Have you all been using AI for orchestration on Claude as well? I've been using Gemini for a few projects recently (more in terms of managing large document sets, not coding) but the memory and lack of context can be quite limiting in terms of overall use. On the plus side, for ~£9 per month I'm getting a lot of usage out of 3.8 Flash and only ran out of tokens once in a few months.

 

[sHo0sH]

On the project linked it's purely Claude for everything

Have you all been using AI for orchestration on Claude as well? I've been using Gemini for a few projects recently (more in terms of managing large document sets, not coding) but the memory and lack of context can be quite limiting in terms of overall use. On the plus side, for ~£9 per month I'm getting a lot of usage out of 3.8 Flash and only ran out of tokens once in a few months.

Been tracking the plan with an artifact (sorry for the massive image that I can now see is completely illegible)

 

[mid_gen]

Have you all been using AI for orchestration on Claude as well? I've been using Gemini for a few projects recently (more in terms of managing large document sets, not coding) but the memory and lack of context can be quite limiting in terms of overall use. On the plus side, for ~£9 per month I'm getting a lot of usage out of 3.8 Flash and only ran out of tokens once in a few months.

Most people using Claude will be using Claude Code as their harness, so Opus 5.5 is the default model for all orchestration and subagents, although you can change to whatever is suitable for your task.

 

[mid_gen]

Haiku 5.5 out today. About time because Haiku 4.5 has been obsolete for months. Can't see myself moving away from deepseek v4.1 flash for summarising work though.

 

[Hades]

I don't see anything about Claude that particularly locks me in. So long as there's a tool a bit like Claude Code it can slot right in and do the same job.

This is the reason some of the AI companies are calling for regulation. It's not to make AI safer. It's to block competitors.

 

[Cromulent]

I've been using Claude for a couple of months now and it works well for my needs. I don't entirely trust it write large amounts of code for me though. I prefer for it to tell me what I need to do and then implement the code myself.

 

[Dr Jack]

I've been using Claude for a couple of months now and it works well for my needs. I don't entirely trust it write large amounts of code for me though. I prefer for it to tell me what I need to do and then implement the code myself.

I don't blame you but you really need to try it out writing code. I think it will surprise you.

I'm not signing up to team software factory just yet, but Claude Code is increasingly capable of writing serious code. I think it's a mistake to just plain vibe code stuff you plan on keeping but it's great for knocking up disposable tools without supervision and can be trusted to build substantial components of your project with minimal supervision providing you provide suitable guidance to start with. The thing I really appreciate about it is that I can get it do stuff while I work on something else (in a different copy of the repository! NEVER run it in the one you're working in unless it's just explaining stuff).

 

[Cromulent]

I don't blame you but you really need to try it out writing code. I think it will surprise you.

I'm not signing up to team software factory just yet, but Claude Code is increasingly capable of writing serious code. I think it's a mistake to just plain vibe code stuff you plan on keeping but it's great for knocking up disposable tools without supervision and can be trusted to build substantial components of your project with minimal supervision providing you provide suitable guidance to start with. The thing I really appreciate about it is that I can get it do stuff while I work on something else (in a different copy of the repository! NEVER run it in the one you're working in unless it's just explaining stuff).

I guess I'll try it out with some small stuff until I get used to using it for bigger stuff. I do have some ideas I'd like a bit of help with so that might be a good fit.

 

[mid_gen]

I've been using Claude for a couple of months now and it works well for my needs. I don't entirely trust it write large amounts of code for me though. I prefer for it to tell me what I need to do and then implement the code myself.

I don't know how anyone is wasting time writing code by hand anymore, you might as well go back to making punch cards if you're going to be that archaic.

Are you not using Claude Code? The Claude chat app?

If not, then you really need Claude Code, if you think having Claude tell you what to do is impressive, wait to CC starts smashing out stuff for you. I'm a 20+ year professional software developer, and I trust CC to write excellent code these days. Even just a year ago it needed a lot of handholding, but in the last six months it's reached a tipping point where there's simply no reason to write code by hand anymore.

 

[Cromulent]

I don't know how anyone is wasting time writing code by hand anymore, you might as well go back to making punch cards if you're going to be that archaic.

Are you not using Claude Code? The Claude chat app?

If not, then you really need Claude Code, if you think having Claude tell you what to do is impressive, wait to CC starts smashing out stuff for you. I'm a 20+ year professional software developer, and I trust CC to write excellent code these days. Even just a year ago it needed a lot of handholding, but in the last six months it's reached a tipping point where there's simply no reason to write code by hand anymore.

I do use Claude code in Visual Studio Code. I guess it just comes down to trust. As I said above I'll try using it for more work and see how it goes.

 

[Rroff]

I don't know how anyone is wasting time writing code by hand anymore, you might as well go back to making punch cards if you're going to be that archaic.

On a serious note I use a lot of tricks which AI has no ability to do as things stand (and/or I'd have to get the agent to go back in and implement in every specific case where it would be useful and if doing something to optimise code at a global level have to keep track of that manually anyhow) and/or do really esoteric things like misusing Raw Input to interface with an ATtiny85 as a HID device to work around the lack of support for a serial USB interface, etc. (which AI has no clue about).

I also enjoy the process of working up code and find quiet satisfaction in really nailing a neat optimised implementation.

 

[mid_gen]

On a serious note I use a lot of tricks which AI has no ability to do as things stand (and/or I'd have to get the agent to go back in and implement in every specific case where it would be useful and if doing something to optimise code at a global level have to keep track of that manually anyhow) and/or do really esoteric things like misusing Raw Input to interface with an ATtiny85 as a HID device to work around the lack of support for a serial USB interface, etc. (which AI has no clue about).

Oh I'm using all the little performance tricks and stuff I've learned throughout my career. I've included it all in the agent instructions so it doesn't need specific prompting, it just implements features exactly as I would do it myself.

Literally just a few months ago I would be watching it like a hawk and frequently jumping in to change things and correct it. It's partly down to just learning how to use them effectively, partly down to the models improving, but they have been 'good enough' for a few months now.

I also enjoy the process of working up code and find quiet satisfaction in really nailing a neat optimised implementation.

The craft of software engineering is satisfying for sure, but I find much more satisfaction in just being able to implement things I would never have dreamed of allocating the time and resources to do previously. I built some systems yesterday that would have taken months if I was working by hand.

In a way I'm lucky that my trade is game development, because games are fundamentally an emotional product, the aim is to put the software in front of a player and have them feel some emotions, and LLMs will never be able to do that part. The crafting of a gameplay experience is a uniquely human skill. If I was just producing enterprise software in this environment I would be pretty uninspired with the career outlook tbh!

 

[Dr Jack]

I don't know how anyone is wasting time writing code by hand anymore, you might as well go back to making punch cards if you're going to be that archaic.

I don't know how you can maintain and improve your skills or keep up with the shape of your codebase if you're never writing code.

I do a blend. Today I got Claude to port a load of shaders for me, while I was working on combining those shaders into a procedural parchment texture generator. That's the stuff I find I really enjoy about AI code -- the ability to offload tasks onto it while I keep on coding myself.

 

[mid_gen]

I don't know how you can maintain and improve your skills or keep up with the shape of your codebase if you're never writing code.

I didn't say I never *read* code. I'm frequently discussing the shape of the codebase and doing regular ongoing maintenance, refactors, improvements.

Using coding agents and vibe coding are not the same thing.