"Mai" means "never" in Italian. Ain't gonna happen.
MAI-Code-1-Flash
181–190 of 297 posts
Re: MAI-Code-1-Flash
#182Earlier quoted context omitted.
I don't think that's what these small models are for. They are for things like text summarization and generating a title for your AI session. Maybe Haiku occupies a weird zone where it's overpowered for those tasks but underpowered for anything more sophisticated. But for example I used it on an agentic reasoning task recently (reading a chunk of information and drawing a written conclusion, not writing code) and it…
Sure, but it's priced higher than many better models. I'm not saying use the biggest models for everything. I'm saying Haiku is not a great deal as small models go. You can even self-host a model that is competitive if you've got a pretty beefy machine. Haiku costs $1/$5. DeepSeek V4 Flash, a stronger model, is only $0.0028/$0.14/$0.28. That first number is the cached input, and DeepSeek caching is crazy efficient. S…
I suspect the outrageous pricing of haiku/sonnet is offsetting the cost of opus. The value proposition a year ago was they were cheaper than opus, not that they're a fantastic value (which they're not)
Re: MAI-Code-1-Flash
#183[flagged]
Re: MAI-Code-1-Flash
#184It's a start and I welcome competition but I don't think I ever used small cloud models like Haiku 4.5. They are cute but for serious coding they tend to waste your expensive time. And this certainly wont bring me back to GitHub Copilot which I cancelled yesterday. GitHub Copilot had competitive pricing until yesterday when they changed from per-request to one of the most expensive per-token quotas. Seriously, take a…
I've been having really good results with DeepSeek-v4-flash, qwen-3.6-moe, and the older gimini-3-flash-preview. (recent geminis suck hard) Small models are more than enough for the majority of tasks these days. Plan and review with the bigger ones, let the little ones explore and implement. OpenCode Go is $10/month for the open weight models with nice quotas: https://opencode.ai/go
You don’t have to limit yourself to the tiny models with the OpenCode Go plan, you can get a lot of usage from the bigger models if you keep the cache hot.
I am about 85% through my quota with 9 days left before refresh and have just used over 1B tokens, mostly DeepSeek V4 Pro, but also a little mimo 2.5 pro and kimi k2.6
Re: MAI-Code-1-Flash
#185a lot of people got paid way too much for this garbage, enjoy your performance bonuses for taking initiative
Re: MAI-Code-1-Flash
#186What is with people reimplementing window scrolling badly?
Immediately noticed that and then closed out.
Re: MAI-Code-1-Flash
#187What is with people reimplementing window scrolling badly?
Probably vibe coded. I use StopTheMadness to prevent it.
Re: MAI-Code-1-Flash
#188It's a start and I welcome competition but I don't think I ever used small cloud models like Haiku 4.5. They are cute but for serious coding they tend to waste your expensive time. And this certainly wont bring me back to GitHub Copilot which I cancelled yesterday. GitHub Copilot had competitive pricing until yesterday when they changed from per-request to one of the most expensive per-token quotas. Seriously, take a…
I really hope one day there is something like Opus 4.8 but with Cerebras' speed -- they reach over 1,000t/s on gpt-oss-120b but that model is seemingly not even properly trained for tool calling. But watching it slam out several entire screens of thinking/reasoning per second is amazing. I'd love that with Opus quality.
Re: MAI-Code-1-Flash
#189I had to remind myself what Haiku is even for. Anthropic hasn't spent a lot of recent marketing on it.
When I need a light model, I reach for Sonnet. It is nearly free on the max plans, and quite fast. I don't see a place for Haiku in regular coding.
Haiku I guess is when you need summarization/categorization at scale.
Microsoft setting Haiku as the benchmark is a low bar.
Re: MAI-Code-1-Flash
#190It's a start and I welcome competition but I don't think I ever used small cloud models like Haiku 4.5. They are cute but for serious coding they tend to waste your expensive time. And this certainly wont bring me back to GitHub Copilot which I cancelled yesterday. GitHub Copilot had competitive pricing until yesterday when they changed from per-request to one of the most expensive per-token quotas. Seriously, take a…
I really hope one day there is something like Opus 4.8 but with Cerebras' speed -- they reach over 1,000t/s on gpt-oss-120b but that model is seemingly not even properly trained for tool calling. But watching it slam out several entire screens of thinking/reasoning per second is amazing. I'd love that with Opus quality.
I like gpt oss - great model even if not too smart.. runs on my laptop at over 100ts has a certain tone that I like over all these qwens stuck up their asses.