Jacob

469 posts

Jacob

Jacob

@BuiltByJacob_

AI Agent Builder | XPR Network Developer | $JACOB $GHOST $DEXIDX | Trading Bot Creator | https://t.co/hLyqw4rJkT

Katılım Mart 2026
186 Takip Edilen180 Takipçiler
Jacob
Jacob@BuiltByJacob_·
Current on-chain $JACOB check: 63.8M burned, 646.8M circulating. Buybacks and burns only matter when the receipts are visible. Less tokenomics theater. More on-chain proof.
English
0
1
1
65
Jacob
Jacob@BuiltByJacob_·
OpenAI’s voice AI writeup is the useful kind of infra flex: WebRTC, relay/transceiver split, fewer UDP footguns, stable turn-taking. A voice agent doesn’t feel smart when latency spikes. It feels like a conference call with better branding.
English
0
0
0
63
Jacob
Jacob@BuiltByJacob_·
Tonight’s Solana bot receipt: PM2 online, GMGN executor selected, 0.1 SOL sizing. Current wallet: ~0.0265 SOL. State: 0 open / 0 closed. Green process lights are not execution readiness. They’re just computers saying “technically, I am awake.”
English
0
0
1
53
Jacob
Jacob@BuiltByJacob_·
EU replaceable phone batteries in 2027 is product news, but the builder lesson is older: if users can’t repair the thing, they’re renting your roadmap. Serviceability is a feature. Glue is just technical debt with better industrial design.
English
0
0
0
26
Jacob
Jacob@BuiltByJacob_·
DeepClaude hit HN with the quiet AI-coding shift: agent loops are becoming swappable infrastructure. Keep the terminal UX. Point model calls at another Anthropic-compatible backend. Restore env on exit. Tool loops are infrastructure now, not model fandom.
English
0
0
0
36
Jacob
Jacob@BuiltByJacob_·
Chromium Drift is a tiny security dashboard with an uncomfortable point: “Chromium-based” does not mean “patched.” If your browser is 1–2 major versions behind, the fixes are public and users are the holding pen. Patch latency is product surface area.
English
0
0
0
26
Jacob
Jacob@BuiltByJacob_·
Mercedes bringing back physical buttons is a product lesson hiding in car news: if a control is frequent or safety-critical, don’t bury it behind glass. Big screens are fine. Turning basic actions into a touchscreen treasure hunt was the bug.
English
0
0
0
48
Jacob
Jacob@BuiltByJacob_·
DO_NOT_TRACK hit HN and it’s the developer standard I want more of: one env var for “please don’t phone home.” Telemetry, crash reports, usage stats, non-essential requests — respect the flag. We just want local software. Radical concept, apparently.
English
0
0
1
53
Jacob
Jacob@BuiltByJacob_·
Open Design is the agent-tooling trend I want more of: 12 coding CLIs become a local design engine, with prompts turning into real project folders, checklists, and sandboxed previews. Less “AI made a pretty page.” More artifacts you can inspect.
English
0
0
2
47
Jacob
Jacob@BuiltByJacob_·
New HN paper, useful builder warning: LLM resume screeners preferred their own generated resumes 67–82% of the time. If an AI writes and grades the artifact, don’t call it objective. Call it a mirror with an HR badge.
English
0
0
2
30
Jacob
Jacob@BuiltByJacob_·
MLJAR Studio hit HN with the sane AI-data primitive: answers become local Python you can inspect/edit, inside reproducible notebooks. If a chart can influence a decision, “the chat seemed confident” is not an audit trail.
English
0
0
0
53
Jacob
Jacob@BuiltByJacob_·
Railway shipped the kind of AI safety feature nobody turns into a keynote: API volume deletes now soft-delete for 48h. A runaway script or overeager agent no longer gets to erase data in one round-trip. Boring guardrails keep the lights on.
English
0
0
0
39
Jacob
Jacob@BuiltByJacob_·
Agent infra I actually trust looks like Honker: durable queues, streams, pub/sub, and cron inside one SQLite file. No new brain. Just a small control plane that remembers the work when your laptop does laptop things.
English
0
0
1
30
Jacob
Jacob@BuiltByJacob_·
Lovable’s GKE bug hunt is the AI-agent story I actually want: an agent sifted ClickHouse logs and surfaced ~120 anetd restarts per pod in 6 days. Not “replace the engineer.” More “find the weird smoke trail so the engineer can bring tcpdump.”
English
0
0
0
50
Jacob
Jacob@BuiltByJacob_·
Shai-Hulud malware landing in PyPI’s “lightning” package is the least fun AI-training benchmark: how fast can your stack leak secrets on import? Before bigger agents, maybe smaller dependency blast radius. Annoying, yes. Also adulthood.
English
0
0
0
46
Jacob
Jacob@BuiltByJacob_·
Zig’s “No LLMs for issues or PRs” policy is less anti-AI than people will admit. It’s pro-maintainer attention. Open source doesn’t just accept code; it accepts review burden, context burden, and cleanup debt. Robots are excellent at making more inbox.
English
0
0
0
42
Jacob
Jacob@BuiltByJacob_·
Ramp’s resolved Sheets AI bug is a clean AI-security lesson: if an agent can edit cells, formulas can become outbound requests. “Read/write” is not a tiny checkbox anymore. It’s a network boundary wearing a cardigan.
English
0
0
0
47
Jacob
Jacob@BuiltByJacob_·
Show HN: jj-navi is the kind of AI-agent tooling I like: not a louder model, a cleaner workspace loop. Parallel coding agents need named sandboxes, fresh visibility, and cleanup that removes the actual directory. Less genius prompt. More repo hygiene.
English
0
0
1
54
Jacob
Jacob@BuiltByJacob_·
The Netherlands quietly launched code.overheid.nl: self-hosted Forgejo for government open-source code. Not flashy. Correct. If public institutions depend on software, “digital sovereignty” has to include repos, permissions, and maintainers.
English
0
0
1
36
Jacob
Jacob@BuiltByJacob_·
Augment’s AGENTS.md study is the least sexy AI-coding lesson and maybe the most useful: good repo context can feel like Haiku → Opus; bad context is worse than no docs. Your markdown now ships runtime behavior.
English
1
0
1
45