11,504 karma · joined July 6, 2012
So it sounds like helping customers with databases full of red flags is their bread and butter
No, their email templating tool finds an old throwaway repo you did 6 years ago, templates its name into a form email, and invites you to join a cattle call to be whiteboarded along with the rest of the shmucks
I didn't see people on here ranting and taking up the flag of revolution for the TPS report excel paster guy's job that they were automating away with their web2 SaaS startup.
But wait- that guy himself was automating away the job of the lady who used to physically Xerox the TPS report and put it in the filing cabinet down the hall, but that lady was automating the job of the secretary who used to re-type all those TPS reports.
It's automatic filing cabinets all the way down, and ranting because your little slice of the filing cabinet automation machine has been made redundant is a bit silly.
Can you "prove" that GPT2 isn't concious?
> Here is why that is backwards. I just showed that a different edit format improves their own models by 5 to 14 points while cutting output tokens by ~20%. That’s not a threat. It’s free R&D.
He makes it sounds like he got a 5-14% boost on a top level benchmark, not 5% improvement on a narrow find and replace metric. Anecdotally, I don't usually have a lot of issues with editing in Claude Code or Cursor, and if there is an issue the model corrects it.
Assuming that it costs double the tokens when it has to correct itself, and find and replace errors are as prominent in actual day to day use as his benchmark, we're talking a 5% efficiency gain in editing token use (not reasoning or tool use). Given that editing must be less than 1/3 of the token use (I assume much less?), we're talking an overall efficiency gain of less than 1%.
This seems like a promising technique but maybe not a high priority in efficiency gains for these tools. The messianic tone, like assuming that Google cut off his access to suppress his genius editing technique rather than just because he was hammering their API also leaves a bad taste, along with the rampant and blatant ChatGPTisms in the blog post.
> But the operation is also a media venture: Garry’s List started with a blog pillorying public-sector unions as “special interests,” attacking the ongoing teachers’ strike, and denouncing the proposed billionaire tax.
- Public sector unions are special interests. This is a plain fact.
- The current teacher's strike in San Francisco, even if it succeeds, will only push the district into insolvency, prompting a state takeover. The state will then cut much more aggressively. Maybe this would be a good thing though, although probably not what the union intended. Advocates of the strike are literally demanding the district spend its reserves on a couple years of raises.
- I'm certainly no billionaire, but the proposed tax will do nothing more than push the extremely small and mobile group of billionaires to take their business elsewhere. It's unlikely to raise tax revenues over the long run.
> Lisa Gelobter, a computer scientist who helped shape the modern web by leading the team that developed the animation technology used to create GIFs.
Looks like the GIF was invented by CompuServe in 1987?
> CompuServe introduced GIF on 15 June 1987 to provide a color image format for their file downloading areas. This replaced their earlier run-length encoding format, which was black and white only. GIF became popular because it used Lempel–Ziv–Welch data compression.
```markdown # Run NNNN
## First Impressions [What state is the project in? What did the last agent leave?]
## Plan [What will you work on this iteration? Why?]
## Work Log [Fill this in as you work]
## Discoveries [What did you learn? What surprised you? What should the next agent know?]
## Summary [Fill this in before committing] ```
This is surprisingly effective and lets agents easily continue in progress work and understand past decisions.
```
Rules:
- Only one disk can be moved at a time.
- Only the top disk from any stack can be moved.
- A larger disk may not be placed on top of a smaller disk.
For all moves, follow the standard Tower of Hanoi procedure: If the previous move did not move disk 1, move disk 1 clockwise one peg (0 -> 1 -> 2 -> 0).
If the previous move did move disk 1, make the only legal move that does not involve moving disk1.
Use these clear steps to find the next move given the previous move and current state.
Previous move: {previous_move} Current State: {current_state} Based on the previous move and current state, find the single next move that follows the procedure and the resulting next state.
```
This is buried down in the appendix while the main paper is full of agentic swarms this and millions of agents that and plenty of fancy math symbols and graphs. Maybe there is more to it, but the fact that they decided to publish with such a trivial task which could be much more easily accomplished by having an llm write a simple python script is concerning.