Péter Szilágyi ✓

@peter_szilagyi · joined 02 Sep 2010

Founder @dark_dot_bio | Former Go Ethereum Lead (2015-2025)

72 402Followers

393Following

12 360Posts total

128.4KViews on collected posts

Ultimi post

Péter Szilágyi ✓@peter_szilagyi13 Sep

😇 https://t.co/wOvdFxPIPH

721 views · 4 likes · 0 reposts · 1 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi11 Sep

Dark Bio teaser ;) - "Ser, what do I see here?" - "The tool through which AI operates your Ark!" 🤯 https://t.co/JRasd3zwsu

2.5K views · 4 likes · 0 reposts · 1 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi11 Sep

@peter_szilagyi I had opposite on a .net codebase in all honesty 5.1 fixed it in hours, opus and astra spent weeks of tokens (resets on astra) and still did not fix. for me 5.1 is far better so it seems "it depends" 1.4K views · 4 likes · 0 reposts · 1 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi11 Sep

@peter_szilagyi give openserv a spin. its an inference api with a reasoning compiler, makes agents more reliable and you can use smaller models and get the same/better results - https://t.co/Tzcd9EHRjo 398 views · 25 likes · 1 reposts · 1 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi11 Sep

@peter_szilagyi Honestly just use opus instead of fable, the results are so similar between them at a fraction of the cost 4.1K views · 5 likes · 0 reposts · 3 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi11 Sep

After using Astra heavily for a week concurrently with Fable... it's lightyears better :/ - Faster: same bug 45 vs 9 mins to track down. - Cheaper: 1 day is enough for me to max out my $200 Fable sub for the week; takes me 2 days on Astra on $100. - Better: Fable makes bad bugs. 64.5K views · 435 likes · 5 reposts · 51 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi10 Sep

Writing network protocols with Claude and Codex feels like mounting a constant social engineering attack against the LLM. You need to talk to it just right so it doesn't freak out and throw out the thread due to "cyber protections". 3.6K views · 30 likes · 0 reposts · 3 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi26 May

This is a first draft. We'll keep iterating on it in the coming months as the system develops and as we hear back from readers. Comments, corrections, and pushback are all welcome. 2.3K views · 16 likes · 0 reposts · 0 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi26 May

Read it here: https://t.co/NMALFldJhP 2.8K views · 30 likes · 0 reposts · 1 replies Open on X →

Péter Szilágyi ✓@peter_szilagyi26 May

Dark Bio whitepaper is out! We're building a system in which a person's health data, their genome most of all, no longer has to live with a custodian to be useful. A system, where data does not move, rather stays on a small device the owner holds. https://t.co/zScmBuyRNo

46.1K views · 618 likes · 63 reposts · 40 replies Open on X →

Rispetto ad account della stessa dimensione

7 post degli ultimi 90 giorni, accanto alla fascia di 10K–100K follower. copertura nella norma per la sua dimensione, reazione più debole della media.

Visualizzazioni mediane2 455questo account1 002mediana per 10K–100K

Copertura, %3.39%questo account3.71%mediana per 10K–100K

Interazione, %0.69%questo account1.64%mediana per 10K–100K

Metrica	Questo account	Mediana per 10K–100K	Rapporto
Visualizzazioni mediane per post	2 455	1 002	2.45×
Copertura (visualizzazioni ÷ follower)	3.39%	3.71%	0.91×
Tasso di interazione	0.69%	1.64%	0.42×

Altri account di questa fascia → Confronta con un altro account → Come sono costruiti questi parametri →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

46.1K26 May

2.8K

2.3K

3.6K10 Sep

64.5K11 Sep

4.1K

398

1.4K

2.5K

72113 Sep

Last 10 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

1.56%26 May

1.12%

0.68%

0.92%10 Sep

0.76%11 Sep

0.19%

6.78%

0.35%

0.20%

0.69%13 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.64%.

What the audience does

Likes69.2%1 171 in total

Reposts4.1%69 in total

Replies6.0%102 in total

Bookmarks20.6%349 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Ultimi post

Rispetto ad account della stessa dimensione

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Account simili