171–180 of 481 posts
Note this is the 07/31 release of DSv4 flash and not the "preview" that they put out a couple months or so ago. I've been running this model locally for a week, and the preview version before that. This updated one feels like a whole tier up. It's very capable for debugging and analyzing documents/data I upload. The killer feature, IMO, is the speed. On 2x RTX Pro 6000 Blackwell, its ~8k tok/s prefill and ~250 tok/s…
Earlier quoted context omitted.
They need to be able to serve their market. The price increase is partly load shedding. If they improve their ability to serve their load, they can always drop it again, as OpenAI did with Luna recently.
> as OpenAI did with Luna recently My read is, OpenAI is neither able to claw b2b money (away from Ant) nor are they able to stave off open weights on the other. In short, they're struggling to hold onto their distant #2 position in the coding market, and these pricing changes reflect a (desperate) change in strategy.
the private endpoint costs 10x (azure).
private endpoints for deepseek (lots of providers) also cost about 10x more.
but 10x more for deepseek is $0.028 cached input, and 10x more for luna is $0.10.
This is on Pi agent, nothing fancy at all about my prompts or use case. Anyone else experiencing this?
I've also had it randomly go from talking about Rust to talking about the electric chair, controversies about D&D rules (both irrelevant and something I've never discussed) and it's completely blind to it in future prompts even when its pointed out and referenced directly
All this said its still worth it but the agentic performance has degraded in my experience at least
Compared to the last Deepseek V4 Flash version I've had tons of issues with it getting in infinite loops and talking to itself without executing tool calls, wasting tons of tokens This is on Pi agent, nothing fancy at all about my prompts or use case. Anyone else experiencing this? I've also had it randomly go from talking about Rust to talking about the electric chair, controversies about D&D rules (both irrelevant…
When it was first available in opencode, it was kinda slow for me, I guess because everyone wanted to try the new shiny. But now it's back to being screamingly fast and Opus 4.8 level of smart, for penies.
I've been using it extensively since the release and the best summary I can give is that it's good enough to use it for (almost) everything and cheap enough that the cost are irrelevant. I'm running it in Oh My Pi with a second instance running as "advisor" and even with 5-6 active sessions (effectively 12 streams) I'm struggling to spend more than 5 bucks per day. OpenCode Go even has double limits temporarily so fo…
Kimi K3 was an interesting model only a month ago, and now we're looking at the same performance for 1/20th of the price. Wild how fast this is advancing.
Real question: is there anybody that is both maintaining alpha-dev capability by keeping abreast of all these daily changes, while also reserving enough time to actually work? Seems like we've reached the event horizon of whether AI advances are worth paying attention to.
I recommend opencode or something akin to it to play with models. Any big model updates or hot new ones will naturally run across your desk that way
I've been using it extensively since the release and the best summary I can give is that it's good enough to use it for (almost) everything and cheap enough that the cost are irrelevant. I'm running it in Oh My Pi with a second instance running as "advisor" and even with 5-6 active sessions (effectively 12 streams) I'm struggling to spend more than 5 bucks per day. OpenCode Go even has double limits temporarily so fo…
And software keeps getting worst. The analogy I like is that building software is running a Michelin restaurant. The moment you scale, the chef is just writing cooking books and is absent, and you move into franchising, you will be amazed at the bottom line revenue scaling, while customers will be progressively appalled with the food...
Earlier quoted context omitted.
not at all true. if you're truly using it across the board for smaller things (translation of pages, filtering of every individual tweet based on its relevance to you etc), the costs ramp up super quickly. i used for work where i did less and it quickly reaches thousands if you're not careful. i can already see what some will say: skill issue et cetera - whatever.
I thought it went without saying that GPT 5.6 Sol is the wrong model to use for things like filtering tweets. Apparently not?
I've been using it extensively since the release and the best summary I can give is that it's good enough to use it for (almost) everything and cheap enough that the cost are irrelevant. I'm running it in Oh My Pi with a second instance running as "advisor" and even with 5-6 active sessions (effectively 12 streams) I'm struggling to spend more than 5 bucks per day. OpenCode Go even has double limits temporarily so fo…
Does auto generating tests even do anything helpful? Don’t they just sort of tautologically say the code does what it does at best or do something completely ridiculous like test and implementation that only exists in the test file at worst?