Hacker News Reader

Comment by nylonstrung | Hacker News Reader

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 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

View on HN

I think this one requires a bit of strong prompting. I am also normally a Pi user, but my experience in OpenCode with this model has been drastically better than in Pi, where it overthinks a lot and gets distracted by random things.

It might be even better in Codex or Oh My Pi according to this bench I saw earlier: https://nitter.net/composio/status/2085330847951970801

What quantization are you using? Which infra provider?

Baseten.co's version got into a loop rather rapidly... I've since added loop detection and adjusted some other settings on the pi coding agent and have yet to notice it again. I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet and it's the top provider on openrouter.ai volume wise.

If memory serves the DeepInfra offering is marked as fp4 because that's the native precision of the experts (which are of course the majority of the weights in a MoE model) so they feel that's the more accurate label, while most other providers claim fp8 because the dense layers are natively fp8 and they want to display the bigger number for obvious reasons. They're not actually serving at different precisions, it's just a confusing mess.

using the platform.deepseek API version I haven't had this happen once in my usage (which has been exclusive since its release). Which provider are you using? I also use a pretty bare bones Pi.

I've been using for work, from opencode $10/mo subscription plan, on high effort (which is better than max imo), and haven't had any issue.

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.

Yeah, I saw the same thing - quite annoying. It can be mitigated through the prompt.

Reply on news.ycombinator.com