Viewing profile — dandiep

Why are LLMs producing this super tense text more often now? Is it because they are being optimized to use fewer tokens?

Hopefully Gemini 3 fine tuning is released sometime soon. Failing that, what other recommendations do people have?

Will GPT 5.5 fine tuning be released any time soon?

For me, the biggest hurdle to writing a PWA is the insane installation process [1]. There are also a ton of quirks, eg I don’t think you can update the icon if it’s installed as a …

Anyone know why OpenAI hasn't released a new model for fine tuning since 4.1? It'll be a year next month since their last model update for fine tuning.

For me, Codex does well at pure-coding based tasks, but the moment it involves product judgement, design, or writing – which a lot of my tasks do – I need to pull in Claude. It is …

99% of what I do is fine-tuned models, so there is a certain level of commitment I have to make around training and time to switch.

For someone looking to switch over to Gemini from OpenAI, are there any gotchas one should be aware of? E.g. I heard some mention of API limits and approvals? Or in terms of prompt…

I tried this! Me: Is it possible get early access to the GPT 5 fine tuning? It is much better at non-English languages, which is the majority of what we do, so it would be greatly …

Still no GPT 5.x fine tuning? I emailed support a while back to see if there was an early access program (99.99% sure the answer is yes). This is when I discovered that their suppo…

100% agree. Will never understand the love for the global menu bar, it makes no sense.

Isn’t this solved in 3.14/PEP-649?

I've been using yt-dlp to download transcripts. Are there alternatives that don't require going through all these hoops? I'm guessing no.

Whisper is unusable IMO because of the hallucinations. Widely documented. Removing silence from audio clips helps, but even then it will auto correct grammar, translating bilingual…

I wish Google would provide a WebRTC endpoint for their Live mode like Open AI does for their Realtime models [1]. Makes it so much easier to deploy without needing something like …

Appreciate the efforts. It’s not there yet, but when it gets there it will open up a lot of use cases. Any fine tuning for s2s in the horizon?

100% and I’ve done this, but it’s still there.

1) Previous TTS models had problems with major problems accents. E.g. a Spanish sentence could drift from a Spain accent to Mexican to American all within one sentence. Has this be…

This is a fantastic idea. Now how to get it on RDS…

Clearly crypto should be a sinking ship with people swimming to the shores of other places in this metaphor

Has anyone had great success with voice mode following their system prompts? Every time I try the quality seems markedly less than the normal gpt-4o model.