TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Bard is much worse at puzzle solving than ChatGPT

90 pointsby cowllinabout 2 years ago

13 comments

hackpertabout 2 years ago
Wow I had hoped for a more productive discussion than these 1-1 comparisons of Bard vs ChatGPT that I'm seeing everywhere. The model deployed with this version of Bard is clearly a smaller model than the biggest LaMDA/PaLM models Google has been working on for ages. Which, according to their publications, show unprecedented results on _proof writing_ of all things (see Minerva). While their strategic decisions may be questionable (or they're just trying to quantize the model for mass deployment without burning billions per month in compute costs), its almost silly to question Google's ability to build useful LLMs.
评论 #35258055 未加载
评论 #35258474 未加载
评论 #35258090 未加载
评论 #35259350 未加载
评论 #35257492 未加载
评论 #35257356 未加载
评论 #35257899 未加载
评论 #35258747 未加载
评论 #35258817 未加载
fenomasabout 2 years ago
Am I missing something? Most of TFA is about Bard failing to answer with rhyming words, but in the only prompts shown the author doesn&#x27;t actually <i>ask</i> for rhyming words. He just says the hint and the name of the puzzle.<p>Is this not simply: &quot;Bard is worse than ChatGPT at having seen the &#x27;how-to-play&#x27; page for my side project during its training&quot;?
评论 #35257585 未加载
jackblemmingabout 2 years ago
How is this possible? Google makes people do 8 rounds of leetcode. How could they be beaten? Nothing makes sense anymore.
评论 #35257824 未加载
评论 #35258069 未加载
SteveNutsabout 2 years ago
It&#x27;s so sad to me to see the downfall of google from the absolute coolest company on the planet to the one that&#x27;s now trying to keep up.
评论 #35257008 未加载
kodahabout 2 years ago
That&#x27;s a clever game to get it to play. Today I asked ChatGPT to give me 1000 Fibonacci numbers starting with the 2000th number and it crashed. Later I asked it the same prompt and it repeatedly gave me code to calculate the Fibonacci numbers in Python.
评论 #35257069 未加载
评论 #35257270 未加载
boffinismabout 2 years ago
&gt; Twofer Goofer HQ&#x27;s adherence to strict &quot;perfect&quot; rhyme can be tricky for those slant rhyme-inclined.<p>And yet one puzzle they hammer Bard for failing is &quot;Cactus Practice&quot;. What accent do you have to have for that to be a perfect rhyme?
评论 #35258331 未加载
评论 #35258704 未加载
visargaabout 2 years ago
Offtopic - have you seen Phind?<p><a href="https:&#x2F;&#x2F;www.phind.com&#x2F;">https:&#x2F;&#x2F;www.phind.com&#x2F;</a><p>It is very fast and wins the search benchmarks here:<p><a href="https:&#x2F;&#x2F;twitter.com&#x2F;vladquant&#x2F;status&#x2F;1638305110869807104" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;vladquant&#x2F;status&#x2F;1638305110869807104</a>
评论 #35258347 未加载
mikewarotabout 2 years ago
If I understand how Large Language models work, they don&#x27;t actually know about spelling.... they are given tokens that represent words, and can only infer things from the context of those tokens across terabytes of data that they&#x27;re given.<p>Any rhyming done is an impressive result.
评论 #35257051 未加载
评论 #35260099 未加载
评论 #35257323 未加载
评论 #35258126 未加载
milemiabout 2 years ago
&quot;Bard is much worse than ChatGPT at solving an obscure word game I invented&quot; would have been a more honest title, but would probably generate less clicks for the author.<p>Bard may still be much worse than ChatGPT at solving all kinds of puzzles, but the article is click bait for promoting the author&#x27;s word game, not an actual investigation that warrants that conclusion.
评论 #35257651 未加载
评论 #35257144 未加载
porphyraabout 2 years ago
How do you navigate this blog to read the other articles? I couldn&#x27;t find any way to read the one on gpt4 (clicking the underlined &quot;wrote about&quot; does nothing) and twofergoofer.com&#x2F;blog goes to a 404.
评论 #35257141 未加载
评论 #35258352 未加载
ralfdabout 2 years ago
It is interesting how lackluster the reactions are about Bard, when it would have been jaw-gapping amazing just a year ago.
masakreTechabout 2 years ago
Bard is basically trash
NoZebra120vClipabout 2 years ago
I tried to play hangman with it, but it was on crack.