Yep, the Brin effect- he'd come into projects that were well along and undermine them by saying "why don't you just..." and then everybody would pivot to his idea, which was rarely practical enough to work.
I disagree. If the group encounters any institutional blockers, Brin can wave them away instantly. Of course, he can slow things down as well presumably because he's not a SME.
I feel like someone with his experience and background should have the self awareness to help avoid that scenario. However I agree it's still a possibility...
I think he believes he’s the ultimate unblocker. Just find all the points of friction and wave a wand and cut through the bureaucracy, force supporting teams to help, force facilities to fix weird problems, etc.
A tiny example I heard: he overheard an employee (who was working on some urgent project he parachuted into) complaining that it was hard working late in this particular office because the closest microkitchen had slim pickings by the end of the day. He stops the conversation and asks a few followup questions. For the rest of the project it was always fully stocked with all the best snacks and drinks, milk and cereal always topped off, fruit always available, etc. I don’t remember the exact details (it’s been a decade since I heard this story) but I remember thinking it went above and beyond what I had available close to my own desk. They thought the dinner spread at the closest cafeteria got better too, but they didn’t know if it was a coincidence or if he made it happen.
I’m sure there’s a ton of the “the boss said something and we’re overreacting” effect. But so much of Google has ossified and slowed that I’m sure it’s also helpful to have a walking sudo command to make the org work for you.
From what I hear, he directly expedited an office move just to bring Gemini folks together in NYC. So that is true to some degree. Not sure about the whole picture.
I would say the exact opposite. When you take someone that smart and then they become a billionaire and spend all their time around people telling them that everything they say and do is amazing, my prior would be any self-awareness he may once have had will have evaporated long ago.
> I don't see how that can make the project move faster. I wouldn't be surprised it has the opposite effect actually.
Possibly. But you surely already realized that business is a lot about "showing off", in this case showing off that AI is a matter for decision at the top level.
I think they're probably tied up in public relations hell. They are too big and too brand protective to risk launching something that has even the tiniest chance of producing content they could get slammed for. They're likely spending all their time on adding layer upon layer of moderation to prevent that from happening. It would be better to just ship and get ahead of it by doing a demo that contains a weird response and use that as an opportunity to educate people on what they need to be careful of when using the tool. They could spin that into them being honest and having their user's interests at heart. Unfortunately, they also have to worry about what their advertising partners think which is the bigger problem.
I agree with this, Google has to account for a lot of things before making anything public compared to other smaller players. Otherwise, huge fines are on the way. I hate that some policy makers don't understand anything about technology, but still try to impose rules that don't make any sense.
Assuming this is true the impact of this very defensive brand position is that being defensive and risk averse IS the brand. In the long run your actions speak louder than words.
I do think it's a bit ridiculous (although quite possibly true) that they would be wary what advertisers think. The ad platform is full of terrible AI options already.
They need a pause to diffuse the hype thus lowering unrealistic expectations.
I can expect a slew of articles to that effect shortly.
Otherwise, people will continue to expect miracles, so whatever Google may release will be a huge disappointment.
The simplest answer is probably the right one: Gemini, or at least the Gemini models that Google believes it can serve to customers in a cost effective way, simply isn't up to par. A release where Gemini manages to be at where OpenAI was three months ago would objectively be an achievement, but it'd be a disappointment and disastrous for investor's outlook for Google. So the delay is to kick the can down the road a bit and hope for some miraculous development that substantially improves quality.
The rate at which the Transformer architecture can learn and adapt to new information is astounding - so it makes absolutely no sense to me that they can't manage to throw 200 data annotators at their model and make it best-in-class.
They did sink capital into Anthropic recently so perhaps that shuffled things up internally / changed some roadmaps?
If that's the case - Anthropic's models are extremely capable and can be easily launched to the top of the leaderboards if they go for a less belligerent training approach.
> Google representatives earlier this year told some cloud customers and business partners they would get access to the company’s new conversational AI
See, that's the difference between OPENai and old g
Really? In my experience, it's worse than chatgpt 3.5.
I had it answer me things like "this model, which costs 38k€ is cheaper than this other one, which costs 29k€". I've never seen ChatGPT make such basic mistakes.
Search is just a tool for LLMs. Ask Bing Chat about tomorrow’s expected Starship launch and it will do a decent job.
Likewise with 3rd party extensions; a good LLM will make the best choice based on criteria.
In a way the LLM becomes the end user from a search/advertising perspective. The actual end user just expects an answer, not a list of 5 ads and 10 possible places to go look for the answer.
So yeah, search as an activity still exists, it’s just much less monetizable because the value prop of LLMs is distilling all that noise to a useful answer.
‘A decent job’ is really subjective here. You don’t get to see the pictures from the article it’s summarizing, which may be ok for something as routine as a Starlink launch, but doesn’t help for a hurricane forecast where you want to see its path on a map etc.
I rarely just want an answer when I am doing a search. But when I do I generally care more about accuracy than I am willing to trust a LLM.
This whole product category is barely a year old and you’re pointing out its (real) limitations?
If we’re talking about the viability of the search ads business in the next few months, sure, those are good reasons people will stay with traditional search and therefore be monetizable.
But as an industry trend, I think search will be 100% LLM intermediated pretty quickly. Pics of a subject, projections of hurricane routes… I’d be very surprised if both aren’t provided by LLMs within 12 months.
But won’t LLMs be monetized in the exact same ways search has been? If you’re asking Bing Chat instead of searching Google for the best hotels in a city, you bet people are gonna wanna pay to make sure their name comes up.
If anything, I can see this poses more of a risk to websites than to Google. You’re still querying a knowledge graph representation of the internet, it’s only really the last step (clicking a link to a third party website from the SERP) that disappears.
AI can clearly move past these limitations, but it won’t be an LLM it will be some other technique.
If anything in the next 12 months I expect LLM’s to get worse in many areas as people start doing the equivalent of SEO to get LLM’s to say whatever they want. It’s GPT 5.0+ vs companies trying to sell stuff etc.
LLM kind of suck doing web searches, asking for SpaceX launch date is faster with google. Asking it for a stock market summary, it will suck hard comparing to just loading the first page of wsj. Most real time news tasks will suck vs Google, where it excel is remassaging info that it has been trained on like coding and how tos
I am not sure about stock market summary and similar stuffs. I created a stock earnings report summariser [1] using the recently announced GPT from OpenAI. It is pretty handy and cool. This is not something Google can replicate for everybody’s niche needs.
Here, I just went to chatgpt and asked it two questions -- it now just automatically searches bing:
> can you explain what's currently going on with the israel palestine situation?
ChatGPT
The current situation in the Israel-Palestine conflict, as of November 2023, is characterized by ongoing hostilities and a deepening humanitarian crisis. Key aspects include:
Human Impact and Fighting: As of November 13, 2023, the death toll in Gaza has reached 11,100, including more than 8,000 children and women. The collapse of medical centres and communication services in Gaza has made it difficult to update casualty figures. Israeli air raids have continued, and there have been fatalities on both sides, including Israeli soldiers and Palestinian fighters .
Gaza’s Hospitals in Crisis: Gaza’s medical infrastructure is under severe strain. The second largest hospital in Gaza, al-Quds, ceased operations due to a fuel shortage. Al-Shifa Hospital, another major hospital, is struggling with numerous challenges, including handling the bodies of those killed in the bombardment and having to close its doors to new patients. There are ongoing international concerns about firefights in hospitals endangering innocent patients and staff .
Diplomatic Efforts and International Response: Diplomatic efforts are ongoing to address the crisis. The UN has been involved in memorials for colleagues killed in Gaza. U.S. President Joe Biden has engaged in discussions with Qatar's Emir regarding the protection of civilians and the need for humanitarian aid in Gaza. There has been a call for an immediate ceasefire, and Hamas has suspended hostage negotiations in response to how Israel handled the situation at al-Shifa Hospital .
West Bank Developments: There have been reports of fatal incidents in the West Bank, including the shooting of a Palestinian man by Israeli forces. The Palestinian Health Ministry has reported the deaths of at least 186 Palestinians in the West Bank since October 7. Clashes and explosions have been reported in areas like Nablus and Qalqilya .
This situation is complex and continues to evolve, with significant human suffering and widespread international concern. The ongoing conflict, coupled with the humanitarian crisis in Gaza and the West Bank, remains a focal point of international diplomatic efforts and media attention.
User
> what started the current fighting
ChatGPT
The current Israel-Hamas conflict, which escalated into a war in October 2023, began on October 7, 2023. This escalation was initiated by Hamas, the Palestinian Sunni Islamist group, which is designated as a foreign terrorist organization by the United States. Hamas launched an unprecedented and multifaceted assault on Israel from the Gaza Strip, involving attacks by land, sea, and air. This offensive included a massive barrage of rockets fired into southern Israel in the early morning hours of October 7, with the impacts of these attacks being felt as far as Tel Aviv and Beersheba .
These actions marked a significant escalation in the longstanding conflict between Israel and Hamas and led to a severe humanitarian crisis and a high number of casualties. As of mid-November 2023, the conflict had resulted in the deaths of over 12,000 people, including civilians and journalists from various nations .
The complexity and intensity of this conflict highlight the deeply rooted tensions and the ongoing struggle in the region, with each new incident contributing to a cycle of violence and retaliation.
I'm just pointing out that it can talk about current events perfectly well with an integration, it's not a fundamental issue if you're building a product around an LLM.
Saying it can do something based on evidence of it failing to do that very thing isn’t convincing. Summarizing the first search result isn’t the same as actually giving the information someone is looking for.
Further the assumption that search engines would allow OpenAI to leverage their work while running them out of business is extremely suspect. So if the argument LLM’s will replace search engines while leveraging them is poorly thought out.
I almost never go to google search first if i want to know something anymore. ChatGPT is often my first last and only resort (along with some trips to wikipedia or documentation or whatever to verify)
I agree but I think it's more complicated than that. Advertisers have become very prudish about what content their ads are shown next to and LLMs have been getting a lot of media flak about bias and hallucinations and copyright infringement which might scare off advertisers. They might be having a really hard time selling this to advertisers which could be holding things up. Also, ChatGPT is ad free so if Gemini isn't clearly better then a lot of people won't switch.
ChatGPT 3.5 is free, but GPT4 is not. I can see a lot of people using something as good or better than GPT4 that is supported by ads and no monthly fee.
> OpenAI got to iterate, but maybe Google instantly move 37'd conversational AI?
If you write such speculative theories, I want to do, too. :-)
What if Google already "37'd" OpenAI, but the result is too dangerous to be released to the public, i.e. it takes a huge amount of work to "defuse"/"cripple" their AI for it to be suitable for "public consumption".
What if Google has an actual GAI that is so good they’ve secretly turned over all strategic decisions to it, and it is directing this “appear to be behind” strategy for reasons known only to itself?
If anyone was going to create Samaritan [1] and end the world, of course it would be Google. The AI would probably bring about the apocalypse trying to sunset the main search engine in a misguided fit of madness brought on by analyzing Google's past behavior [2]
> However, DeepMind considers Sparrow a research-based, proof-of-concept model that is not ready to be deployed, said Geoffrey Irving, a safety researcher at DeepMind and lead author of the paper introducing Sparrow.
> “We have not deployed the system because we think that it has a lot of biases and flaws of other types,” said Irving. “I think the question is, how do you weigh the communication advantages — like communicating with humans — against the disadvantages?
Seems less speculative than a company with more resources, more know-how, more talent, more training data, more compute, more product experience, more anything, somehow unable to ship a competing product. But that seems the common conclusion people draw.
Google will be a shell of the former glory by the end of the decade and we'll all by baffled at how they fumbled it from such a position of dominance. Honestly the only parts of their brand I can see surviving it are YouTube, maps and Android. Everything else is completely fair game for disruption and some of it is just laying there on the table for the taking (e.g Image search and actually Search in general), heck YouTube could even be replaced if TikTok made a long form feed.
We've watched them be total top of the field world wide in machine learning, things they demoed over a decade ago now were basically magic then they proceeded to do absolutely nothing with the tech and just leave it to rot, now look at them scramble to finally try and implement some of that into reality and their organizational structure just isn't up for the task.
Current CEO needs to sit in all ML meetings for a week, figure out who knows how to operate and build it, who's stopping it from leaving the labs, separate the implementation wheat from the bureaucratic chaff, metaphorically lock the wheat in a skunkworks for a month and tell them they have to demo in 3 weeks and ship something when the doors are unlocked at the end of the month.
I do think the one area that Alphabet is still genuinely innovating is Waymo. With Cruise sidelined, if they can manage to turn it into something that makes money (have ridden in SF, and the tech seems to work great), it could be up there with Youtube & Android, maybe even bigger.
I don't see how that can make the project move faster. I wouldn't be surprised it has the opposite effect actually.