back
user profile
Alifatisk
6,513karma·3,495submissions·October 14, 2022
recent activity (3,495 total)
comment
There is also Hopper for ObjC/Swift, haven't tried it personally though https://www.hopperapp.com
comment
There is MCPs for Ghidra
comment
Title could have mentioned this relates to Openclaw/moltbot/clawdbot too. Now the post became more relevant to read when I realized what this was about.
comment
Wow, the Qwen team is pushing out content (models + research + blogpost) at an incredible rate! Looks like omni-modals is their focus? The benchmark look intriguing but I can’t stop thinking of the hn…
comment
> Europol has used "Palantir Gotham" for a decade at this point. Europol did use a customized version of Gotham from 2016 up until 2022 where they decommissioned it and has replaced it in…
comment
Are the collection of components run in some kind of namespace? Say I run a Pies for Gitlab (which in itself had lots of components), and I run a Pies for Frpd, do they share the same space or are the…
comment
> It’s so vast that Microsoft distributes it with a sophisticated GUI installer where you navigate a maze of checkboxes, hunting for which “Workloads” or “Individual Components” contain the actual …
comment
No, GLM-5 is being rolled out to Max and Pro users first. They will later roll out to Lite users when capacity allows.
comment
I don’t think it is about viability. The Christmas discount was supposed to expire jan 15, then it was further expanded to jan 31. The deal was too good to miss out on.
comment
From their email titled ”GLM-5 and New Z.ai Chat Coming!” > Availability Note: GLM-5 is currently available exclusively on Max and Pro Coding Plan users. We are working to scale our infrastructure …
comment
”Training Hardware: Huawei Ascend” https://glm5.net https://www.digitalapplied.com/blog/zhipu-ai-glm-5-release-7... But now after digging deeper into it, I noted that…
comment
While GLM-5 seems impressive, this release also included lots of new cool stuff! > GLM-5 can turn text or source materials directly into .docx, .pdf, and .xlsx files—PRDs, lesson plans, exams, spre…
comment
I noted there is a new toggle between "agent/chat" when you switch to GLM-5 on chat.z.ai. I assume this model is focused on agentic tasks. Can't wait for them to release the paper …
comment
yt-dlp is a blessing
comment
I agree, I tried RE using multiple tools connected to MCP and a agent, it was tasked to recreate what the source code might have looked like from a binary and what possible vulnerabilities there could…
comment
I wasn’t only referring to their new model, I meant their blogpost and the research behind their progress, its always a joyride to read. I didn’t know it was this serious with the vocabulary, I’ll be …
comment
As always, the Qwen team is pushing out fantastic content Hope they update the model page soon https://chat.qwen.ai/settings/model …
comment
They can only raise prices as long as people buy their subscriptions / pay for their api. The Chinese labs are closing in on the SOTA models (I would say they are already there) and offer insane …
comment
Project feels unfinished, I don't even know how to get started.
comment
Oh I see
comment
I have been waiting for a project like this since last year when someone on Twitter mentioned it. I can finally doomscroll without my brain rotting. Update, it does not run properly in Firefox on iOS.…
comment
Pricing for step-3.5-flash: - Input: $0.1/1M tokens - Output: $0.3/1M tokens Its an MoE 196B param model with 11b active params. It handles a context window of 256k tokens. > by employing…
comment
It was on the morning news today
comment
I use GLM-4.7 by Z.ai. For authentication mechanism, I guess you mean when the agent calls for the model? It’s through api keys. The subscription I have is the coding plan lite (3x usage of the Claude…