Seems llm progress really is plateauing. I guess that was to be expected.
This is a performance update to a previous generation model. It's not a new model.
I’m fully aware.
Improved Gemini 2.5 Flash and Flash-Lite
271–280 of 285 posts
Re: Improved Gemini 2.5 Flash and Flash-Lite
#272Seems llm progress really is plateauing. I guess that was to be expected.
And this existing model’s update is evidence how? What were your expectations of this update? I actually even agree that the progress is plateauing, but your comment is a non-sequitur.
I’ll admit it is a bit of a non-sequitur. Just feels like the news I see on HN about LLMs is less groundbreaking every day and more becoming normal/boring
Re: Improved Gemini 2.5 Flash and Flash-Lite
#273Re: Improved Gemini 2.5 Flash and Flash-Lite
#274Earlier quoted context omitted.
And this existing model’s update is evidence how? What were your expectations of this update? I actually even agree that the progress is plateauing, but your comment is a non-sequitur.
I’ll admit it is a bit of a non-sequitur. Just feels like the news I see on HN about LLMs is less groundbreaking every day and more becoming normal/boring
This article is about Google improving something. Sounds pretty out of the ordinary to me
Re: Improved Gemini 2.5 Flash and Flash-Lite
#275Earlier quoted context omitted.
why use grok? It seems like it's constantly being throttled in order to appear more right-wing
It’s actually not. Most of the time if you ask it about a contentious political issue it will either give you a balanced view or a left-leaning one. Try it and see for yourself.
I just saw elon's tweet saying they'll fix it whenever the response is not rightwing enough
Re: Improved Gemini 2.5 Flash and Flash-Lite
#276Earlier quoted context omitted.
I just asked Gemini Flash to do this. I included the instruction to use regular expressions to do the conversion to ANSI. It gave me a reasonable Python function which boils down to calling `re.sub()` for each of bold, italic and underline. For italics: text = re.sub(r'(\*|_)(.+?)\1', replace_italic, text, flags=re.DOTALL) The `replace_italic` is a one line callback function surrounding the re's match with the ANSI c…
I asked Gemini 2.5 Flash to just write me a function to do it, and it used regex. In a separate chat, I asked it to suggest some ways to do it first, and it provided three alternatives, but suggested I started with regex. FWIW I used Open WebUI, which uses the API (via OpenRouter). I've seen people here mentioning that the API produces much better results than the chat app, for whatever reason. For reference, here's…
> I asked it to suggest some ways to do it first
Yes, this is a very effective tactic, in my experience! Especially when I am asking for a solution where I am not confident I know what is "best". Having a "pre chat" to settle "what to do" and then "how to do it" before finally telling the LLM to "do it" is often worth the extra time for getting it to provide a solution for complex problems.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#277Earlier quoted context omitted.
I just asked Gemini Flash to do this. I included the instruction to use regular expressions to do the conversion to ANSI. It gave me a reasonable Python function which boils down to calling `re.sub()` for each of bold, italic and underline. For italics: text = re.sub(r'(\*|_)(.+?)\1', replace_italic, text, flags=re.DOTALL) The `replace_italic` is a one line callback function surrounding the re's match with the ANSI c…
> I included the instruction to use regular expressions to do the conversion to ANSI. The viber coders (who I referred to in my comment) aren't giving implementation tips. What did it give you before you put an implementation tip into your prompt? ======= FWIW, if you're at all interested, here's my implementation: def markdown_ansi_code_subst(mdstr: str, src_pattern: str, replacement_start: str, replacement_end: str…
The prompt was:
> Give me a Python function that takes a string holding text in Markdown markup syntax and that uses regular expressions to replace any Markdown markup codes for bold, italics and underline with their ANSI equivalent.
BTW, your solution will produce bad output. Markdown's "bold" etc markup comes in pairs of markers and your simple replacement will match singlets.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#278Earlier quoted context omitted.
I’ll admit it is a bit of a non-sequitur. Just feels like the news I see on HN about LLMs is less groundbreaking every day and more becoming normal/boring
This article is about Google improving something. Sounds pretty out of the ordinary to me
Hahaha fair
Re: Improved Gemini 2.5 Flash and Flash-Lite
#279Ok wow these models are great and fast! Tested it for pdf extraction tasks.
Re: Improved Gemini 2.5 Flash and Flash-Lite
#280I still can't understand how functioning adults believe that releasing their work in two separate places is a good idea (Ai Studio and Vertex AI).
Don’t forget they also have two versions for their genaisdk and you can also use their genaisdk through vertex great! Best part is all LLMs get horribly confused as well and mix different sdks etc.