HNHacker News
TopNewBestAskShowJobs

harrisonjackson

1,520 karma · joined December 7, 2012

Founder of Spike Labs - gen AI and chatbot lab

hiring@spikelabsinc.com

submissionscomments
harrisonjackson··on OpenAI: Streaming is now available in the Assistants API
This and/or being able to fetch the responses with their token usage by id. What is that ID for without a way to retrieve the completions with it?
harrisonjackson··on Readability.js
This is pretty good for stuffing web scrapings into an LLM context.

Can also use `JSDOM ---> element.textContent` depending on your needs. Useful for snagging all the text content or a specific element's.

harrisonjackson··on Replicate vs. Fly GPU cold-start latency
I spent a couple months hacking on a dreambooth product that let users train a model on their own photos and then generate new images w/ presets or their own prompts.

The main costs were:

- gpu time for training

- gpu time for inference

- storage costs for the users' models

- egress fees to download model

I ended up using banana.dev and runpod.io for the serverless gpus. Both were great, easy to hook into, and highly customizable.

I spent a bunch of time trying to optimize download speed, egress fees, gpu spot pricing, gpu location, etc.

R2 is cheaper than s3 - free egress! But the download speeds were MUCH worse than s3 - enough that it ended up not even being competitive.

It was frequently cheaper to use more expensive GPUs w/ better location and network speeds. That factored more into the pricing than how long the actual inference took on each instance.

Likewise, if your most important metric is time from boot to starting inference then network access might be the limiting factor.

harrisonjackson··on My favorite database shirts
Before clicking through I had that mongodb shirt in mind as my personal favorite.

I got a few of them at aws reinvent in like 2012.

2nd favorite is a Cassandra one of similar make.

harrisonjackson··on OpenAI board in discussions with Sam Altman to return as CEO
Now seems like the perfect time for him to go raise, bring over the team he wants, and retain ownership and control in a more effective way than a non-profit. Idk why he would go back without BOD capitulating a lot.
harrisonjackson··on Show HN: Nango – Open unified API for product integrations
Nice yall - love the updates

You have built a really great product that is easy to use. I've tested out the self-hosted option on render.com with neon postgres and the cloud version. Both are super easy to get up and running.

Now, it is no exaggeration to say that the most annoying part of adding a new integration is just navigating the API provider's portal to get the app outh creds.

harrisonjackson··on Jury Finds Realtors Conspired, Awards Nearly $1.8B in Damages
Inspectors maybe since they go on site and climb around etc... but every other profession you listed uses the same documents/software for every single deal so I don't know what you mean by "real" work.
harrisonjackson··on Ask HN: PG's 'Do Things That Don't Scale' manual examples?
Counter examples might be useful. Many startups implode under the weight/pressure of doing the wrong things that don't scale.

It should lead to growth/revenue/whatever your north star is.

harrisonjackson··on Mazda slaps developer with cease-and-desist for DIY smart home integration
I am curious what an "expensive" one would actually cost, too... It is a car so already a large purchase. I'd pay a bit more for an accurate thermostat.
harrisonjackson··on Confessions of a Netflix DVD Dead-Ender
Movie Trading Company - https://movietradingcompany.com/

IRL if you can - they're awesome.

The one in Dallas is huge. Like a gamestop for dvds but the size of a warehouse. It is pretty close to a Half-priced books, same concept but books, and hitting the two of them back to back is a fun way to spend a day.

harrisonjackson··on I don’t buy “duplication is cheaper than the wrong abstraction” (2021)
> Fast forward a few years

Sounds like it was just what was needed at the time and worked better/longer than most abstractions.

harrisonjackson··on Luck be a Landlord is now banned in 13 countries on the Google Play Store
I think it is great they wrote this post and are bringing attention to the problem. I wish someone had told me all of this before I submitted my first app. It helps to know this is an issue you might run into and it is not the end of the process and it does not mean your app won’t get approved.

Rallying devs and their community of users is worthwhile. My advice was more for how to respond and handle the review process internally with google and Apple based on what has actually worked ime ¯\_(ツ)_/¯

harrisonjackson··on Luck be a Landlord is now banned in 13 countries on the Google Play Store
One of least effective ways to argue your case is by pointing to other apps that have the same violations. I say that having submitted 50+ apps across various categories and dealing with thousands of app review exchanges to get them released. You can find apps that violate all sorts of guidelines and laws and it is super frustrating when yours gets blocked but it is part of the business.

Did they slip by a reviewer that didn't care? Did they use their "VC" illuminati connections? Are they such a big player the rules don't apply? It doesn't really matter or have anything to do with getting YOUR app released and the reviewer you are talking to will most likely ignore that completely.

Your best bet is to remove or change the mechanic if possible, resubmit, and then add it back in during a future update if you feel strongly about it.

It is possible those other apps have something that allows them to keep it... and by communicating nicely and earnestly with your reviewer you might find a way to skirt the rules, if a way exists. For us, it was frequently tweaking copy or TOS or other minor changes that allowed us to release an app with only superficial changes that the initial review made it seem like we were totally screwed. I do get the instinct to just say FU though.

harrisonjackson··on Why is OAuth still hard in 2023?
Nice read from nango team. FWIW we are using nango/nango cloud in prod to support ~15 integrations.

We signed up before they had an admin dashboard and did everything over cli. It was easy then and even easier now. We have also contributed a couple of providers when they didn't have apis we wanted to use setup yet (Stripe, Zapier NLA). They have an open slack channel and we were able to get them shipped immediately.

harrisonjackson··on Richer UI install available for desktop
I am using this to elevate a couple high use “tabs” out of the browser so I can more easily toggle to them with CMD+tab. It’s better than pinning the tabs all the way to the left of 100 other open tabs ¯\_(ツ)_/¯

Other than that not getting much utility out of it but that’s fine

harrisonjackson··on ManyCam dishonored my lifetime license
Companies that acquire lifetime users should have a budget set aside for refunding these users.
harrisonjackson··on Problems with AWS Amplify and its use of DynamoDB
I use amplify in lots of projects. It is a nice wrapper for the auth and registration stuff. We also use it for some frontend ci/cd. Nothing else though.

Custom authorizer in front of aws lambda with serverless framework works great with amplify’s frontend api client.

We also use dynamodb serverless but not with app sync and no graphQL. Would I rather have a good and easy to use serverless Postgres db that played well with aws lambda. Yes. Am I going to switch away because I have to plan my access patterns and indices out carefully… no.

harrisonjackson··on OpenAI tech gives Microsoft's Bing a boost in search battle with Google
The rise of gpt generated content is no doubt degrading search results, as well.

Google must be feeling the squeeze from all over.

harrisonjackson··on Secret ChatGPT plugins can be revealed by removing a parameter from an API call
Not necessarily. Spent some time trying to find all of them yesterday for the plugins that are live and it seems like some are behind an ip whitelist / blocked other ways.
harrisonjackson··on GPT-4
I am interested in how a 32k token context even works. That is so much larger than 4k that I am having a hard time imagining how prompts will change and what sort of output is now possible. That is 50 pages of text. Far larger than most content currently being consumed and generated by LLMs.

Q&A and summarization it will be easy to see improvements as current recursive summarizing and embedding techniques are very "lossy" but outside of improving current use cases what will now be possible??

harrisonjackson··on Gitlab loses one-third of its value after company issues weak forecast
It is especially annoying because of how transparent they are about it. You can follow along in merge requests and issues as they discuss exactly this.
harrisonjackson··on ChatGPT's API is so good and cheap, it makes most text generating AI obsolete
The best thing you can do is lots of testing. Setup an environment where you can isolate the prompt you are working on (the new chat playground is good for this) and load it with a system message and some assistant and user messages then play with it until you get the results you want.

I've had success with a simple system method that is one sentence defining how we are extending chatgpt.

"You are AcmeCoBot an extension of ChatGPT which we have enabled <x, y, z features> to assist users <goal>."

Then a user message with the actual instructions on what you want/need - this is much closer prompting for gpt-3.

user msg 1: Translate the following to German for me... some text assistant msg 1: an example translation

new user msg: Translate the following to German for me...

The model completes these interactions well. We may run 1-10 of these completions before using chatgpt for the last mile message that actually gets sent to a user. It takes a while to wrap your head around using the chatgpt api for a non-chat completion.

harrisonjackson··on I am a model and I know that AI will eventually take my job (2020)
The AI generated images are just going to be that much more toxic for real young people.
harrisonjackson··on ChatGPT get-rich-quick schemes are coming for magazines, Amazon, and YouTube
It is a LOT easier to integrate an openai api endpoint that start something on blockchain.

It is almost hilarious to see these content creators jump ship so quickly after espousing crypto as the end all money printer.

harrisonjackson··on New headless Chrome has been released and has a near-perfect browser fingerprint
We have a chatbot that can send users screenshots of their CMS views (kanban, calendar, tables, gallery, etc) from inside of Slack.

The screenshotting uses puppeteer and chromium and a read-only session to impersonate the user and screenshot their dashboard.

It uses the old version of chromium and there were many gotchas that required a lot of extra scaffolding to actually render ours and other websites like they would on my laptop. This will hopefully make it easier for us to maintain once implemented.

harrisonjackson··on Ask HN: Strategies for working with engineers that are too smart?
If there are sections of code that are too complicated for everyone to safely modify then that is a failure of whoever wrote it and whoever reviewed it. At the time, they may have patted themselves on the back but they need to understand that clever != good.

It isn't clear the hierarchy or size of your team or the longterm strategy/goals of the product development. Someone on the team should be pushing back on these changes as they are being planned out or before they are getting merged in.

Ideally, you have a respected senior/staff/cto engineer that can mentor these "clever" programmers. This person needs to be able to grok all the code and see at a macro level how the whole codebase is evolving.

Re: reading code - I am the same way. I spent years writing objective-c when xcode had the best code completion out there so long names weren't an issue. Long function and variable names and tons of whitespace - it is how all of Apple's libraries were written and how the projects templates were setup ¯\_(ツ)_/¯.

Best recommendation is to adopt a strict style for your codebase and ruthlessly apply it to all new code. Linting should happen automatically. There are tools that will run the linter on just the edited files so you can adopt coding styles 1 file at a time.

harrisonjackson··on Ask HN: Why isn't JSON-RPC more widely adopted?
Most crud apps are not the equivalent of an oil refinery.
harrisonjackson··on Americans duped into losing $10B by illegal Indian call centres in 2022: report
Another giveaway is an extra pause before they start talking. This is call software that lets them dial a bunch of numbers at once until someone answers and it switches the person that answered over to an available headset.

If you answer and say hello and there's an extra second just hang up. They'll call back if it is important.

harrisonjackson··on Massive Southwest Airlines disruption leaves customers stranded
The right credit card, if you have one or can get one, usually includes "insurance" for travel delays, lost luggage, cancellations etc. I always forget about the benefits other than "points" but there are some great ones.

Recently, I was glad I used the right card to book an airbnb which we had to cancel day of check-in. Full refund on a non-refundable airbnb.

harrisonjackson··on John Carmack Leaves Meta
I interpreted this as coerced positivity and forced happiness. Not organic actual emotion from feeling fulfilled and successful within their role.
← PreviousPage 2 of 12Next →