Google just launched Gemini 3.5 Flash to mixed reviews. One of the main criticisms is it’s not as cheap as advertised and is much more expensive than 3.1 Flash. While true, I think they weren’t trying to replace 3.1 “Flash”. They were trying to replace 3.1 “Pro”, and I think they achieved that. I’ve been on Google’s ¥2900/month plan for the last month and have been on Claude’s and Codex’s paid plans before too. My assessment, even after different models have been coming out, is kind of unchanged and easy to explain. Not sure if you guys agree but I see the three like this… Claude Code (Opus and Sonnet)– Best for starting completely new projects from ground zero. It understands and follows through on entire PRD’s the best of all three in this area. Opus 4.7 seems to go down rabbit holes though, often eating more cookies than I wanted to feed it. Codex (GPT 5.4. Not sure about 5.5)– Absolutely the best for hunting down bugs efficiently. Usually one-shots the fixes. Although it seems efficient(don’t think I ever hit my daily limits), it’s slower to finish its work. Gemini 3.1 Pro & Google Stitch – Most cost effective of all three. Best front-end designs period. Has Google search at its fingertips when you want it to check for options for feature building. As of today, 3.5 Flash is supposedly as good as 3.1 and is 4 times faster. I can verify the speed for sure. However, it seems to eat twice as many cookies as 3.1 for the same job. Price per token in/out, while cheaper, makes it a wash. You get the same job done by both 3.1 Pro and 3.5 Flash, roughly the same price, but I guess 3.5 Flash gives you extra speed. Summary...The worst part of Gemini models is that the only way it can one-shot hard bug fixes is to give it pictures, and to explain the step-by-steps the user did to encounter the bug. Codex didn’t need any of that. I could just say the shit don’t work and it fixed it while I watched a YouTube video. Claude was decent at fixing shit but seemed to try too much other shit in the process. I mean, why was Claude attempting to start a game of Kred? It can’t do that without multiple players! Lol. Codex may be the most well-rounded of the three with regard to coding. It’s not great at design. It’s not great at keeping all of my intent on new projects. But in brick-by-brick mode(which includes bug fixes), it’s the best. Claude’s 5-hour limits are infuriating but the models are super smart(they seem to get and keep my intent no matter what). Gemini is the jack of all trades, in the sense that the pro plan gives you access to the entire Google AI ecosystem (Nano Banana, Stitch, Antigravity, NotebookLM) but needs refined/detailed prompts. For now, I’m gonna go for one more month with Google then see how Anthropic is treating their customers. I might go back to them. Not sure I’ll go back to Open AI just yet. Fast bug fixes are great, but not worth it based on just that. One thing that I keep in mind is that I build games. I am not trying to solve complicated math or science problems. Sonnet, GPT 5.4 on medium, Gemini Flash have gotten shit done for me in the past. Cranking up to Opus, GPT 5.4 high and Gemini Pro models for shit in the weeds has worked out fine too, meaning I don’t necessarily need to pay for the model that out-benchmarks all the others. It’s not the models...it’s me and how I learn to use the models to their strengths.

Ideas here should be presented as clearly as the person presenting them is capable of and the person presenting them should welcome any opportunities to make their ideas clearer. Comments here should contribute something useful to the original post. Avoid inadvertently slipping into opposition where a simple request for clarification or a suggested reading would be more productive. Threads in this category are handled as follows. A statement is made in the form of a post consisting of a short Title and a Body of any length. This post should be thoughtfully written, thoroughly proofread (and clearly referenced if appropriate). Someone must offer to mediate the thread. This should not be someone who would be more interested in challenging the statement or idea(s) therein but it should be someone who is interested to learn more. A new thread of this format should not be allowed if another is still awaiting a mediator. Once a mediator has volunteered, the thread is considered open to comments. Anyone that the thread is open to may comment (including the mediator). You are only allowed to have one unresolved comment at a time. You may ask for clarification of any number of points, request references or make any other queries. You may also include any number of statements, quotes, references etc. that give weight to your question(s). However, comments should always seek to improve the original post. The thread should not be considered a platform for debate (that's a different format). The objective here is not to arrive at something that everyone agrees with but simply to arrive at the clearest presentation of the original poster's idea. You're welcome to expand upon one part of a post or disagree entirely, but do so in a separate thread that references this one in whole or in part. When a question is raised, the original poster should edit their original post as best they can to address the question. The original post should be considered something that is being submitted for peer-review. Although the ideas in the original post may be well founded, the presentation of those ideas (the post itself) should not be considered static. Edits should reference the #id of the comment that they are in response to. The mediator is to mark questions as 'Resolved' when they believe they have been adequately addressed. This does not imply that the mediator agrees or disagrees with the statement(s) of either party, only that they believe the original poster has addressed the question adequately or provided a useful source for further understanding. It is also up to the mediator to determine what is a 'useful source' and what is not. (optional) If there are no open comments (questions), the mediator may approve the thread. The thread will be closed to further comments until the original poster decides to reopen the thread or close it entirely. The original poster closes the thread. Although there may be numerous unanswered questions and ways to expand upon parts of the post, the original poster may close the thread at any time. Ideally, this is only done when the original poster believes they have done all they can to support and clarify their original statement. As stated in step 3, anyone is welcome to respond in a new thread provided it is thoughtfully written, thoroughly proofread (and clearly referenced if appropriate).

I'd like to add the ability for moderators to add and edit categories in the near future, and maybe add support for tags as well. A way to make threads private or choose who can see. The search still doesn't work, ah the fun tasks to look forward to are endless. Anyway, even if we do add that functionality. What do you guys think are some good categories worth adding. I was thinking of adding a 'Music' category--we should be able to attach zipped Ableton folders if we wanted to do some music production stuff on here. Maybe a 'Money' category, since that tends to come up a lot.

Not sure if I'm the only one interested in this, since I kinda just went ahead and did it. However, if it's going to get used, there are some improvements worth making. -Finish adding rich-text (text that's format-able). -Change some of the language (eg. the submit button is currently "Ask Your Question") -Add some moderator and administrative functionality --list users --delete users --restrict users, or require approval --promote users to admin or moderator --edit/add categories, change color -Update our forked copy of "simple_discussion" to Bootstrap 5 (it's currently on 4, but we are using Bootstrap 5 here already, so there may be a few conflicts) -Add Bootstrap Icons? -Update the github repos with detailed information including development environment settings.