Github account: www.github.com/dwaltrip
Email: dwaltrip77@gmail.com
- > TextSynth provides access to large language, text-to-image, text-to-speech or speech-to-text models such as Mistral, Llama, Stable Diffusion, Whisper thru a REST API and a playground. They can be used for example for text completion, question answering, classification, chat, translation, image generation, speech generation, speech to text transcription, ...
???
- How many hours until someone else is able to get it to work?
I consider myself a bit of an expert vibe engineer and the challenge is alluring :D
- AI is a tool I use while existing as a human. I’d like to know the relative downsides.
- What’s the easiest way to read a PDF like this on mobile? It’s quite painful the default way.
- In context learning for ya: it’s not supposed to be a literal scientific claim.
- If they game the pelican benchmark, it’d be pretty obvious.
Just try other random, non-realistic things like “a giraffe walking a tightrope”, “a car sitting at a cafe eating a pizza”, etc.
If the results are dramatically different, then they gamed it. If they are similar in quality, then they probably didn’t.
- Children are incredibly smart. All of this was fantasy 15 years ago. Comments like yours are amazing to me…
- Can you provide numbers relative to things many of us already do?
- drive to the store or to work
- take a shower
- eat meat
- fly on vacation
And so on... thanks!
- Any new useful tool must be managed in a way so that one isn’t overly dependent on it.
- google maps
- power tools
- complex js frameworks
- ORMs
- the electrical grid (outages are a thing)
- and so on…
This isn’t a new problem unique to LLMs.
Practice using the tool intelligently and responsibly, and also work to maintain your ability to function without when needed.
- Hah good point. Maybe v1 just pulls the first few lines from man.
- The author is vastly overestimating the general legibility and familiarity of things they happen to know well and are used to.
Boring names are also very generic, by definition, and thus often harder to remember. Especially when there are 10 other similar tools. Is it sql-validator, sql-schema-validator, schema-validate, db-validator, or god knows what else?
Edit: I am in favor of better “sub titles” / descriptive slugs / and so on. As well as names that are a hybrid of creative and descriptive. Sqlalchemy is a good example.
Why isn’t there a command line utility called “whatisthis” with a standard protocol that allows tools to give a brief description of what they are?
It could be extended to package managers as well. E.g “pip whatisthis foo_baz”.
Shit we should create this…
- These are the cutting insights I come to HN for.
- Sounds miserable if you like solving real problems.
- A bit reductive.
- I have architectural discussions all the time with coding agents.
- Holy shit man. Get your gears check, they are grinding hard.
- It’s kind of fun watching this comment go up and down :)
There’s so much evidence out there of people getting real value from the tools.
Some questions you can ask yourself are “why doesn’t it work for me?” and “what can I do differently?”.
Be curious, not dogmatic. Ignore the hype, find people doing real work.
The actual goal is to faithfully replicate the functionality and solve the same use cases with a different set of base technologies.
You describing similar but different instrumental goals, which may help reaching the real goal.
Cheekiness aside, your framing is helpful!