Viewing profile — sdrinf

gemma-4 is an incredibly good model, beating several others five time its' size. Hope Jeff's departure won't impact their next-gen products! And best of success for their new ventu…

hi, great project! Windows support is sorely lacking, though. As someone working a lot with sandboxed LLMs right now, the options-space on windows for sandboxing is _extremely lack…

Just want to echo the recommendation for qwen3.5:9b. This is a smol, thinking, agentic tool-using, text-image multimodal creature, with very good internal chains of thought. CoT ca…

Counterpoint to peeps on this thread: * This approach is the _most consistent_ with retaining anonymity on the internet, while actually helping parents with their issues. If any ag…

Taking the opposite side of that bet, here is why: * even if an openweight model appears on huggingface today, exceeding SOTA, given my extensive experience with a wide variety of …

I'm working on something like this. Specifically, I'm doing recursive self-improvement via autocatalysis -but predominantly in writing/research / search tasks. It's very early, but…

can someone please try running the experiment of "but what if just forking&spinning up an OSS clone, scaling up to take in the migrants, acquire network effects, collect roughly sa…

Besides the editorial control -which openai openly flagged to want to remain unbiased- there is a deeper issue with ads-based revenue models in AI: that of margins. If you want ads…

Note: I strongly recommend against using Novita -their main gig is serving quantized versions of the model to offer it for cheaper / at better latency; but if you ran an eval again…

You have two options: * Use it as a "source": chatgpt -> settings -> apps & connectors -> add it as your connector. This supports only 2 functions: search, and fetch; details: http…

The specific "anomaly" is that claude 4 / opus model _does not know_ because it is _not in its' training data_ what its own model version is; AND because it's training data amalgam…

I actually _like_ this, and so does the comfyweb & weebs who are a very significant portion of the driving force behind calm, decade-long projects.

Follow-up question is big lulz: https://yougov.co.uk/topics/society/survey-results/daily/202... "And how effective do you think the new rules will be at preventing those younger th…

This absolutely works... until, and when network effects kick in. Payment processors have major network effects in that infra setup is expensive, banks need to be onboarded one-by-…

Early-40s here who still does all-nighters. How long is recovery time for you? What does it entails -ie what doesn't work as much as it should / takes longer while you recover?

Mozilla is sooo fucked here. On one hand, it would take them approx ~1 sentence of blog to say "We won't sell your input info to anyone" and this drama goes away. OTOH: if the curr…

O1 for collabing on design docs, o1 for overall structure, break it into tasks per preference / sort; sonnet/o1 for executing each small tasks. O1 is higher quality, more nuanced, …

Cease and desist letters. There are many, many people, and companies who operate under the false belief that the CAN-SPAM act does not apply to them; and eg create new mailing list…

Because hypotheticals have a process of moving into "stuff that's happening", on the timescale of years, decades. Once it's starts happening, speak; if speaking doesn't work, fight…

* IA's most important function (at least for me) is holding copies of the World Wide Web as it was. * Given an annually compounding 30% linkrot, 99.92% of all the content ever publ…

For the moment, the best possible solution seems to me simply disabling auto-updates. On long-term, if supermium can port over the critical fixes from chromium, ubo v2 may still su…

For the moment, the best possible solution seems to me simply disabling auto-updates. On long-term, if supermium can port over the critical fixes from chromium, ubo v2 may still su…

Hey HN, supply chain evaluation question: There is this awesome desktop app called chatbox: https://chatboxai.app/ * 1, https://github.com/Bin-Huang the author is Chinese, from Chi…

This article omits specificity of which GPT model. Re-running the experiment on the EU regulation paper using gpt-4-1106 (the current-best "intelligent" one): https://chatgpt.com/s…